Статті в журналах з теми "Learned priors"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Learned priors.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Learned priors".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Chambers, Claire, Hugo Fernandes, and Konrad Paul Kording. "Policies or knowledge: priors differ between a perceptual and sensorimotor task." Journal of Neurophysiology 121, no. 6 (June 1, 2019): 2267–75. http://dx.doi.org/10.1152/jn.00035.2018.
Повний текст джерелаАнотація:
If the brain abstractly represents probability distributions as knowledge, then the modality of a decision, e.g., movement vs. perception, should not matter. If, on the other hand, learned representations are policies, they may be specific to the task where learning takes place. Here, we test this by asking whether a learned spatial prior generalizes from a sensorimotor estimation task to a two-alternative-forced choice (2-Afc) perceptual comparison task. A model and simulation-based analysis revealed that while participants learn prior distribution in the sensorimotor estimation task, measured priors are consistently broader than sensorimotor priors in the 2-Afc task. That the prior does not fully generalize suggests that sensorimotor priors are more like policies than knowledge. In disagreement with standard Bayesian thought, the modality of the decision has a strong influence on the implied prior distributions. NEW & NOTEWORTHY We do not know whether the brain represents abstract and generalizable knowledge or task-specific policies that map internal states to actions. We find that learning in a sensorimotor task does not generalize strongly to a perceptual task, suggesting that humans learned policies and did not truly acquire knowledge. Priors differ across tasks, thus casting doubt on the central tenet of many Bayesian models, that the brain’s representation of the world is built on generalizable knowledge.
2
Liu, Jiaming, Yu Sun, Cihat Eldeniz, Weijie Gan, Hongyu An, and Ulugbek S. Kamilov. "RARE: Image Reconstruction Using Deep Priors Learned Without Groundtruth." IEEE Journal of Selected Topics in Signal Processing 14, no. 6 (October 2020): 1088–99. http://dx.doi.org/10.1109/jstsp.2020.2998402.
Повний текст джерела
3
Haker, S., G. Sapiro, and A. Tannenbaum. "Knowledge-based segmentation of SAR data with learned priors." IEEE Transactions on Image Processing 9, no. 2 (2000): 299–301. http://dx.doi.org/10.1109/83.821747.
Повний текст джерела
4
Abel, David, David Hershkowitz, Gabriel Barth-Maron, Stephen Brawner, Kevin O'Farrell, James MacGlashan, and Stefanie Tellex. "Goal-Based Action Priors." Proceedings of the International Conference on Automated Planning and Scheduling 25 (April 8, 2015): 306–14. http://dx.doi.org/10.1609/icaps.v25i1.13697.
Повний текст джерелаАнотація:
Robots that interact with people must flexibly respond to requests by planning in stochastic state spaces that are often too large to solve for optimal behavior. In this work, we develop a framework for goal and state dependent action priors that can be used to prune away irrelevant actions based on the robot’s current goal, thereby greatly accelerating planning in a variety of complex stochastic environments. Our framework allows these goal-based action priors to be specified by an expert or to be learned from prior experience in related problems. We evaluate our approach in the video game Minecraft, whose complexity makes it an effective robot simulator. We also evaluate our approach in a robot cooking domain that is executed on a two-handed manipulator robot. In both cases, goal-based action priors enhance baseline planners by dramatically reducing the time taken to find a near-optimal plan.
5
Zhang, Richard, Jun-Yan Zhu, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, and Alexei A. Efros. "Real-time user-guided image colorization with learned deep priors." ACM Transactions on Graphics 36, no. 4 (July 20, 2017): 1–11. http://dx.doi.org/10.1145/3072959.3073703.
Повний текст джерела
6
Roach, Neil W., Paul V. McGraw, David J. Whitaker, and James Heron. "Generalization of prior information for rapid Bayesian time estimation." Proceedings of the National Academy of Sciences 114, no. 2 (December 22, 2016): 412–17. http://dx.doi.org/10.1073/pnas.1610706114.
Повний текст джерелаАнотація:
To enable effective interaction with the environment, the brain combines noisy sensory information with expectations based on prior experience. There is ample evidence showing that humans can learn statistical regularities in sensory input and exploit this knowledge to improve perceptual decisions and actions. However, fundamental questions remain regarding how priors are learned and how they generalize to different sensory and behavioral contexts. In principle, maintaining a large set of highly specific priors may be inefficient and restrict the speed at which expectations can be formed and updated in response to changes in the environment. However, priors formed by generalizing across varying contexts may not be accurate. Here, we exploit rapidly induced contextual biases in duration reproduction to reveal how these competing demands are resolved during the early stages of prior acquisition. We show that observers initially form a single prior by generalizing across duration distributions coupled with distinct sensory signals. In contrast, they form multiple priors if distributions are coupled with distinct motor outputs. Together, our findings suggest that rapid prior acquisition is facilitated by generalization across experiences of different sensory inputs but organized according to how that sensory information is acted on.
7
Liu, Haojie, Han Shen, Lichao Huang, Ming Lu, Tong Chen, and Zhan Ma. "Learned Video Compression via Joint Spatial-Temporal Correlation Exploration." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 11580–87. http://dx.doi.org/10.1609/aaai.v34i07.6825.
Повний текст джерелаАнотація:
Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit the temporal correlation using both first-order optical flow and second-order flow prediction. We suggest an one-stage learning approach to encapsulate flow as quantized features from consecutive frames which is then entropy coded with adaptive contexts conditioned on joint spatial-temporal priors to exploit second-order correlations. Joint priors are embedded in autoregressive spatial neighbors, co-located hyper elements and temporal neighbors using ConvLSTM recurrently. We evaluate our approach for the low-delay scenario with High-Efficiency Video Coding (H.265/HEVC), H.264/AVC and another learned video compression method, following the common test settings. Our work offers the state-of-the-art performance, with consistent gains across all popular test sequences.
8
Zhao, Shengrong, and Hu Liang. "Multi-frame super resolution via deep plug-and-play CNN regularization." Journal of Inverse and Ill-posed Problems 28, no. 4 (August 1, 2020): 533–55. http://dx.doi.org/10.1515/jiip-2019-0054.
Повний текст джерелаАнотація:
AbstractBecause of the ill-posedness of multi-frame super resolution (MSR), the regularization method plays an important role in the MSR field. Various regularization terms have been proposed to constrain the image to be estimated. However, artifacts also exist in the estimated image due to the artificial tendency in the manually designed prior model. To solve this problem, we propose a novel regularization-based MSR method with learned prior knowledge. By using the variable splitting technique, the fidelity term and regularization term are separated. The fidelity term is associated with an “{L^{2}}-{L^{2}}” form sub-problem. Meanwhile, the sub-problem respect to regularization term is a denoising problem, which can be solved by denoisers learned from a deep convolutional neural network. Different from the traditional regularization methods which employ hand-crafted image priors, in this paper the image prior model is replaced by learned prior implicitly. The two sub-problems are solved alternately and iteratively. The proposed method cannot only handle complex degradation model, but also use the learned prior knowledge to guide the reconstruction process to avoid the artifacts. Both the quantitative and qualitative results demonstrate that the proposed method gains better quality than the state-of-the-art methods.
9
Baugh, Lee A., Michelle Kao, Roland S. Johansson, and J. Randall Flanagan. "Material evidence: interaction of well-learned priors and sensorimotor memory when lifting objects." Journal of Neurophysiology 108, no. 5 (September 1, 2012): 1262–69. http://dx.doi.org/10.1152/jn.00263.2012.
Повний текст джерелаАнотація:
Skilled object lifting requires the prediction of object weight. When lifting new objects, such prediction is based on well-learned size-weight and material-density correlations, or priors. However, if the prediction is erroneous, people quickly learn the weight of the particular object and can use this knowledge, referred to as sensorimotor memory, when lifting the object again. In the present study, we explored how sensorimotor memory, gained when lifting a given object, interacts with well-learned material-density priors when predicting the weight of a larger but otherwise similar-looking object. Different groups of participants 1st lifted 1 of 4 small objects 10 times. These included a pair of wood-filled objects and a pair of brass-filled objects where 1 of each pair was covered in a wood veneer and the other was covered in a brass veneer. All groups then lifted a larger, brass-filled object with the same covering as the small object they had lifted. For each lift, we determined the initial peak rate of change of vertical load-force rate and the load-phase duration, which provide estimates of predicted object weight. Analysis of the 10th lift of the small cube revealed no effects of surface material, indicating participants learned the appropriate forces required to lift the small cube regardless of object appearance. However, both surface material and core material of the small cube affected the 1st lift of the large block. We conclude that sensorimotor memory related to object density can contribute to weight prediction when lifting novel objects but also that long-term priors related to material properties can influence the prediction.
10
Yang, Dayi, Xiaojun Wu, and Hefeng Yin. "Blind Image Deblurring via a Novel Sparse Channel Prior." Mathematics 10, no. 8 (April 9, 2022): 1238. http://dx.doi.org/10.3390/math10081238.
Повний текст джерелаАнотація:
Blind image deblurring (BID) is a long-standing challenging problem in low-level image processing. To achieve visually pleasing results, it is of utmost importance to select good image priors. In this work, we develop the ratio of the dark channel prior (DCP) to the bright channel prior (BCP) as an image prior for solving the BID problem. Specifically, the above two channel priors obtained from RGB images are used to construct an innovative sparse channel prior at first, and then the learned prior is incorporated into the BID tasks. The proposed sparse channel prior enhances the sparsity of the DCP. At the same time, it also shows the inverse relationship between the DCP and BCP. We employ the auxiliary variable technique to integrate the proposed sparse prior information into the iterative restoration procedure. Extensive experiments on real and synthetic blurry sets show that the proposed algorithm is efficient and competitive compared with the state-of-the-art methods and that the proposed sparse channel prior for blind deblurring is effective.
11
Dai, Xiaowei, Shuiwang Li, Qijun Zhao, and Hongyu Yang. "Animal Pose Estimation Based on 3D Priors." Applied Sciences 13, no. 3 (January 22, 2023): 1466. http://dx.doi.org/10.3390/app13031466.
Повний текст джерелаАнотація:
Animal pose estimation is very useful in analyzing animal behavior, monitoring animal health and moving trajectories, etc. However, occlusions, complex backgrounds, and unconstrained illumination conditions in wild-animal images often lead to large errors in pose estimation, i.e., the detected key points have large deviations from their true positions in 2D images. In this paper, we propose a method to improve animal pose estimation accuracy by exploiting 3D prior constraints. Firstly, we learn the 3D animal pose dictionary, in which each atom provides prior knowledge about 3D animal poses. Secondly, given the initially estimated 2D animal pose in the image, we represent its latent 3D pose with the learned dictionary. Finally, the representation coefficients are optimized to minimize the difference between the initially estimated 2D pose and the 2D projection of the latent 3D pose. Furthermore, we construct 2D and 3D animal pose datasets, which are used to evaluate the algorithm’s performance and learn the 3D pose dictionary, respectively. Our experimental results demonstrate that the proposed method makes good use of the 3D pose knowledge and can effectively improve 2D animal pose estimation.
12
Perugini, Alessandra, and Michele A. Basso. "Perceptual decisions based on previously learned information are independent of dopaminergic tone." Journal of Neurophysiology 119, no. 3 (March 1, 2018): 849–61. http://dx.doi.org/10.1152/jn.00761.2017.
Повний текст джерелаАнотація:
Both cognitive and motor symptoms in people with Parkinson’s disease (PD) arise from either too little or too much dopamine (DA). Akinesia stems from DA neuronal cell loss, and dyskinesia often stems from an overdose of DA medication. Cognitive behaviors typically associated with frontal cortical function, such as working memory and task switching, are also affected by too little or too much DA in PD. Whether motor and cognitive circuits overlap in PD is unknown. In this article, we show that whereas motor performance improves in people with PD when on dopaminergic medication compared with off medication, perceptual decision-making based on previously learned information (priors) remains impaired whether on or off medications. To rule out effects of long-term DA treatment and dopaminergic neuronal loss such as occur in PD, we also tested a group of people with dopa-unresponsive focal dystonia, a disease that involves the basal ganglia, like PD, but has motor symptoms that are insensitive to dopamine treatment and is not thought to involve frontal cortical DA circuits, unlike PD. We found that people with focal dystonia showed intact perceptual decision-making performance but impaired use of priors in perceptual decision-making, similar to people with PD. Together, the results show a dissociation between motor and cognitive performance in people with PD and reveal a novel cognitive impairment, independent of sensory and motor impairment, in people with focal dystonia. The combined results from people with PD and people with focal dystonia provide mechanistic insights into the role of basal ganglia non-dopaminergic circuits in perceptual decision-making based on priors.
13
Hu, Yueyu, Wenhan Yang, and Jiaying Liu. "Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 11013–20. http://dx.doi.org/10.1609/aaai.v34i07.6736.
Повний текст джерелаАнотація:
Approaches to image compression with machine learning now achieve superior performance on the compression rate compared to existing hybrid codecs. The conventional learning-based methods for image compression exploits hyper-prior and spatial context model to facilitate probability estimations. Such models have limitations in modeling long-term dependency and do not fully squeeze out the spatial redundancy in images. In this paper, we propose a coarse-to-fine framework with hierarchical layers of hyper-priors to conduct comprehensive analysis of the image and more effectively reduce spatial redundancy, which improves the rate-distortion performance of image compression significantly. Signal Preserving Hyper Transforms are designed to achieve an in-depth analysis of the latent representation and the Information Aggregation Reconstruction sub-network is proposed to maximally utilize side-information for reconstruction. Experimental results show the effectiveness of the proposed network to efficiently reduce the redundancies in images and improve the rate-distortion performance, especially for high-resolution images. Our project is publicly available at https://huzi96.github.io/coarse-to-fine-compression.html.
14
Dahlbom, David A., and Jonas Braasch. "Multiple f0 pitch estimation for musical applications using dynamic Bayesian networks and learned priors." Journal of the Acoustical Society of America 145, no. 3 (March 2019): 1814. http://dx.doi.org/10.1121/1.5101633.
Повний текст джерела
15
Baugh, Lee A., Amelie Yak, Roland S. Johansson, and J. Randall Flanagan. "Representing multiple object weights: competing priors and sensorimotor memories." Journal of Neurophysiology 116, no. 4 (October 1, 2016): 1615–25. http://dx.doi.org/10.1152/jn.00282.2016.
Повний текст джерелаАнотація:
When lifting an object, individuals scale lifting forces based on long-term priors relating external object properties (such as material and size) to object weight. When experiencing objects that are poorly predicted by priors, people rapidly form and update sensorimotor memories that can be used to predict an object's atypical size-weight relation in support of predictively scaling lift forces. With extensive experience in lifting such objects, long-term priors, assessed with weight judgments, are gradually updated. The aim of the present study was to understand the formation and updating of these memory processes. Participants lifted, over multiple days, a set of black cubes with a normal size-weight mapping and green cubes with an inverse size-weight mapping. Sensorimotor memory was assessed with lifting forces, and priors associated with the black and green cubes were assessed with the size-weight illusion (SWI). Interference was observed in terms of adaptation of the SWI, indicating that priors were not independently adjusted. Half of the participants rapidly learned to scale lift forces appropriately, whereas reduced learning was observed in the others, suggesting that individual differences may be affecting sensorimotor memory abilities. A follow-up experiment showed that lifting forces are not accurately scaled to objects when concurrently performing a visuomotor association task, suggesting that sensorimotor memory formation involves cognitive resources to instantiate the mapping between object identity and weight, potentially explaining the results of experiment 1. These results provide novel insight into the formation and updating of sensorimotor memories and provide support for the independent adjustment of sensorimotor memory and priors.
16
Zhang, Chen, Riccardo Barbano, and Bangti Jin. "Conditional Variational Autoencoder for Learned Image Reconstruction." Computation 9, no. 11 (October 28, 2021): 114. http://dx.doi.org/10.3390/computation9110114.
Повний текст джерелаАнотація:
Learned image reconstruction techniques using deep neural networks have recently gained popularity and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect information uncertainty. In this work, we develop a novel computational framework that approximates the posterior distribution of the unknown image at each query observation. The proposed framework is very flexible: it handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets. Once the network is trained using the conditional variational autoencoder loss, it provides a computationally efficient sampler for the approximate posterior distribution via feed-forward propagation, and the summarizing statistics of the generated samples are used for both point-estimation and uncertainty quantification. We illustrate the proposed framework with extensive numerical experiments on positron emission tomography (with both moderate and low-count levels) showing that the framework generates high-quality samples when compared with state-of-the-art methods.
17
Yan, Xu, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, and Shuguang Cui. "Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 3101–9. http://dx.doi.org/10.1609/aaai.v35i4.16419.
Повний текст джерелаАнотація:
LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.
18
Xu, Jingzhao, Mengke Yuan, Dong-Ming Yan, and Tieru Wu. "Deep unfolding multi-scale regularizer network for image denoising." Computational Visual Media 9, no. 2 (January 3, 2023): 335–50. http://dx.doi.org/10.1007/s41095-022-0277-5.
Повний текст джерелаАнотація:
AbstractExisting deep unfolding methods unroll an optimization algorithm with a fixed number of steps, and utilize convolutional neural networks (CNNs) to learn data-driven priors. However, their performance is limited for two main reasons. Firstly, priors learned in deep feature space need to be converted to the image space at each iteration step, which limits the depth of CNNs and prevents CNNs from exploiting contextual information. Secondly, existing methods only learn deep priors at the single full-resolution scale, so ignore the benefits of multi-scale context in dealing with high level noise. To address these issues, we explicitly consider the image denoising process in the deep feature space and propose the deep unfolding multi-scale regularizer network (DUMRN) for image denoising. The core of DUMRN is the feature-based denoising module (FDM) that directly removes noise in the deep feature space. In each FDM, we construct a multi-scale regularizer block to learn deep prior information from multi-resolution features. We build the DUMRN by stacking a sequence of FDMs and train it in an end-to-end manner. Experimental results on synthetic and real-world benchmarks demonstrate that DUMRN performs favorably compared to state-of-the-art methods.
19
Shi, Fan, Bin Li, and Xiangyang Xue. "Raven's Progressive Matrices Completion with Latent Gaussian Process Priors." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 11 (May 18, 2021): 9612–20. http://dx.doi.org/10.1609/aaai.v35i11.17157.
Повний текст джерелаАнотація:
Abstract reasoning ability is fundamental to human intelligence. It enables humans to uncover relations among abstract concepts and further deduce implicit rules from the relations. As a well-known abstract visual reasoning task, Raven's Progressive Matrices (RPM) are widely used in human IQ tests. Although extensive research has been conducted on RPM solvers with machine intelligence, few studies have considered further advancing the standard answer-selection (classification) problem to a more challenging answer-painting (generating) problem, which can verify whether the model has indeed understood the implicit rules. In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables. The latent Gaussian process also provides an effective way of extrapolation for answer painting based on the learned concept-changing rules. We evaluate the proposed model on RPM-like datasets with multiple continuously-changing visual concepts. Experimental results demonstrate that our model requires only few training samples to paint high-quality answers, generate novel RPM panels, and achieve interpretability through concept-specific latent variables.
20
Yuan, Jinyang, Bin Li, and Xiangyang Xue. "Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9135–42. http://dx.doi.org/10.1609/aaai.v33i01.33019135.
Повний текст джерелаАнотація:
Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scenes. The mechanism of grouping basic visual elements of scenes into conceptual entities is termed as perceptual grouping. In this work, we propose a new type of spatial mixture models with learnable priors for perceptual grouping. Different from existing methods, the proposed method disentangles the representation of an object into “shape” and “appearance” which are modeled separately by the mixture weights and the conditional probability distributions. More specifically, each object in the visual scene is modeled by one mixture component, whose mixture weights and the parameter of the conditional probability distribution are generated by two neural networks, respectively. The mixture weights focus on modeling spatial dependencies (i.e., shape) and the conditional probability distributions deal with intra-object variations (i.e., appearance). In addition, the background is separately modeled as a special component complementary to the foreground objects. Our extensive empirical tests on two perceptual grouping datasets demonstrate that the proposed method outperforms the stateof-the-art methods under most experimental configurations. The learned conceptual entities are generalizable to novel visual scenes and insensitive to the diversity of objects.
21
Mani, Merry, Vincent A. Magnotta, and Mathews Jacob. "qModeL: A plug‐and‐play model‐based reconstruction for highly accelerated multi‐shot diffusion MRI using learned priors." Magnetic Resonance in Medicine 86, no. 2 (March 24, 2021): 835–51. http://dx.doi.org/10.1002/mrm.28756.
Повний текст джерела
22
Paulun, Vivian C., Gavin Buckingham, Melvyn A. Goodale, and Roland W. Fleming. "The material-weight illusion disappears or inverts in objects made of two materials." Journal of Neurophysiology 121, no. 3 (March 1, 2019): 996–1010. http://dx.doi.org/10.1152/jn.00199.2018.
Повний текст джерелаАнотація:
The material-weight illusion (MWI) occurs when an object that looks heavy (e.g., stone) and one that looks light (e.g., Styrofoam) have the same mass. When such stimuli are lifted, the heavier-looking object feels lighter than the lighter-looking object, presumably because well-learned priors about the density of different materials are violated. We examined whether a similar illusion occurs when a certain weight distribution is expected (such as the metal end of a hammer being heavier), but weight is uniformly distributed. In experiment 1, participants lifted bipartite objects that appeared to be made of two materials (combinations of stone, Styrofoam, and wood) but were manipulated to have a uniform weight distribution. Most participants experienced an inverted MWI (i.e., the heavier-looking side felt heavier), suggesting an integration of incoming sensory information with density priors. However, a replication of the classic MWI was found when the objects appeared to be uniformly made of just one of the materials ( experiment 2). Both illusions seemed to be independent of the forces used when the objects were lifted. When lifting bipartite objects but asked to judge the weight of the whole object, participants experienced no illusion ( experiment 3). In experiment 4, we investigated weight perception in objects with a nonuniform weight distribution and again found evidence for an integration of prior and sensory information. Taken together, our seemingly contradictory results challenge most theories about the MWI. However, Bayesian integration of competing density priors with the likelihood of incoming sensory information may explain the opposing illusions. NEW & NOTEWORTHY We report a novel weight illusion that contradicts all current explanations of the material-weight illusion: When lifting an object composed of two materials, the heavier-looking side feels heavier, even when the true weight distribution is uniform. The opposite (classic) illusion is found when the same materials are lifted in two separate objects. Identifying the common mechanism underlying both illusions will have implications for perception more generally. A potential candidate is Bayesian inference with competing priors.
23
Bae, Jinseok, Hojun Jang, Cheol-Hui Min, Hyungun Choi, and Young Min Kim. "Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 86–94. http://dx.doi.org/10.1609/aaai.v36i1.19882.
Повний текст джерелаАнотація:
We present Neural Marionette, an unsupervised approach that discovers the skeletal structure from a dynamic sequence and learns to generate diverse motions that are consistent with the observed motion dynamics. Given a video stream of point cloud observation of an articulated body under arbitrary motion, our approach discovers the unknown low-dimensional skeletal relationship that can effectively represent the movement. Then the discovered structure is utilized to encode the motion priors of dynamic sequences in a latent structure, which can be decoded to the relative joint rotations to represent the full skeletal motion. Our approach works without any prior knowledge of the underlying motion or skeletal structure, and we demonstrate that the discovered structure is even comparable to the hand-labeled ground truth skeleton in representing a 4D sequence of motion. The skeletal structure embeds the general semantics of possible motion space that can generate motions for diverse scenarios. We verify that the learned motion prior is generalizable to the multi-modal sequence generation, interpolation of two poses, and motion retargeting to a different skeletal structure.
24
Wu, Ziniu, Harold Rockwell, Yimeng Zhang, Shiming Tang, and Tai Sing Lee. "Complexity and diversity in sparse code priors improve receptive field characterization of Macaque V1 neurons." PLOS Computational Biology 17, no. 10 (October 25, 2021): e1009528. http://dx.doi.org/10.1371/journal.pcbi.1009528.
Повний текст джерелаАнотація:
System identification techniques—projection pursuit regression models (PPRs) and convolutional neural networks (CNNs)—provide state-of-the-art performance in predicting visual cortical neurons’ responses to arbitrary input stimuli. However, the constituent kernels recovered by these methods are often noisy and lack coherent structure, making it difficult to understand the underlying component features of a neuron’s receptive field. In this paper, we show that using a dictionary of diverse kernels with complex shapes learned from natural scenes based on efficient coding theory, as the front-end for PPRs and CNNs can improve their performance in neuronal response prediction as well as algorithmic data efficiency and convergence speed. Extensive experimental results also indicate that these sparse-code kernels provide important information on the component features of a neuron’s receptive field. In addition, we find that models with the complex-shaped sparse code front-end are significantly better than models with a standard orientation-selective Gabor filter front-end for modeling V1 neurons that have been found to exhibit complex pattern selectivity. We show that the relative performance difference due to these two front-ends can be used to produce a sensitive metric for detecting complex selectivity in V1 neurons.
25
Yao, Heyuan, Zhenhua Song, Baoquan Chen, and Libin Liu. "ControlVAE." ACM Transactions on Graphics 41, no. 6 (November 30, 2022): 1–16. http://dx.doi.org/10.1145/3550454.3555434.
Повний текст джерелаАнотація:
In this paper, we introduce ControlVAE, a novel model-based framework for learning generative motion control policies based on variational autoencoders (VAE). Our framework can learn a rich and flexible latent representation of skills and a skill-conditioned generative control policy from a diverse set of unorganized motion sequences, which enables the generation of realistic human behaviors by sampling in the latent space and allows high-level control policies to reuse the learned skills to accomplish a variety of downstream tasks. In the training of ControlVAE, we employ a learnable world model to realize direct supervision of the latent space and the control policy. This world model effectively captures the unknown dynamics of the simulation system, enabling efficient model-based learning of high-level downstream tasks. We also learn a state-conditional prior distribution in the VAE-based generative control policy, which generates a skill embedding that outperforms the non-conditional priors in downstream tasks. We demonstrate the effectiveness of ControlVAE using a diverse set of tasks, which allows realistic and interactive control of the simulated characters.
26
Polewski, P., J. Shelton, W. Yao, and M. Heurich. "SEGMENTATION OF SINGLE STANDING DEAD TREES IN HIGH-RESOLUTION AERIAL IMAGERY WITH GENERATIVE ADVERSARIAL NETWORK-BASED SHAPE PRIORS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2020 (August 12, 2020): 717–23. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2020-717-2020.
Повний текст джерелаАнотація:
Abstract. The use of multispectral imagery for monitoring biodiversity in ecosystems is becoming widespread. A key parameter of forest ecosystems is the distribution of dead wood. This work addresses the segmentation of individual dead tree crowns in nadir-view aerial infrared imagery. While dead vegetation produces a distinct spectral response in the near infrared band, separating adjacent trees within large swaths of dead stands remains a challenge. We tackle this problem by casting the segmentation task within the active contour framework, a mathematical formulation combining learned models of the object’s shape and appearance as prior information. We explore the use of a deep convolutional generative adversarial network (DCGAN) in the role of the shape model, replacing the original linear mixture-of-eigenshapes formulation. Also, we rely on probabilities obtained from a deep fully convolutional network (FCN) as the appearance prior. Experiments conducted on manually labeled reference polygons show that the DCGAN is able to learn a low-dimensional manifold of tree crown shapes, outperforming the eigenshape model with respect to the similarity of the reproduced and referenced shapes on about 45 % of the test samples. The DCGAN is successful mostly for less convex shapes, whereas the baseline remains superior for more regular tree crown polygons.
27
Liu, Quande, Cheng Chen, Qi Dou, and Pheng-Ann Heng. "Single-Domain Generalization in Medical Image Segmentation via Test-Time Adaptation from Shape Dictionary." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 1756–64. http://dx.doi.org/10.1609/aaai.v36i2.20068.
Повний текст джерелаАнотація:
Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. This paper studies the important yet challenging single domain generalization problem, in which a model is learned under the worst-case scenario with only one source domain to directly generalize to different unseen target domains. We present a novel approach to address this problem in medical image segmentation, which extracts and integrates the semantic shape prior information of segmentation that are invariant across domains and can be well-captured even from single domain data to facilitate segmentation under distribution shifts. Besides, a test-time adaptation strategy with dual-consistency regularization is further devised to promote dynamic incorporation of these shape priors under each unseen domain to improve model generalizability. Extensive experiments on two medical image segmentation tasks demonstrate the consistent improvements of our method across various unseen domains, as well as its superiority over state-of-the-art approaches in addressing domain generalization under the worst-case scenario.
28
Wu, Benjamin, Chao Liu, Benjamin Eckart, and Jan Kautz. "Neural Interferometry: Image Reconstruction from Astronomical Interferometers Using Transformer-Conditioned Neural Fields." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 3 (June 28, 2022): 2685–93. http://dx.doi.org/10.1609/aaai.v36i3.20171.
Повний текст джерелаАнотація:
Astronomical interferometry enables a collection of telescopes to achieve angular resolutions comparable to that of a single, much larger telescope. This is achieved by combining simultaneous observations from pairs of telescopes such that the signal is mathematically equivalent to sampling the Fourier domain of the object. However, reconstructing images from such sparse sampling is a challenging and ill-posed problem, with current methods requiring precise tuning of parameters and manual, iterative cleaning by experts. We present a novel deep learning approach in which the representation in the Fourier domain of an astronomical source is learned implicitly using a neural field representation. Data-driven priors can be added through a transformer encoder. Results on synthetically observed galaxies show that transformer-conditioned neural fields can successfully reconstruct astronomical observations even when the number of visibilities is very sparse.
29
Zhu, Hongyuan, Xi Peng, Joey Tianyi Zhou, Songfan Yang, Vijay Chanderasekh, Liyuan Li, and Joo-Hwee Lim. "Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9332–39. http://dx.doi.org/10.1609/aaai.v33i01.33019332.
Повний текст джерелаАнотація:
Single image rain-streak removal is an extremely challenging problem due to the presence of non-uniform rain densities in images. Previous works solve this problem using various hand-designed priors or by explicitly mapping synthetic rain to paired clean image in a supervised way. In practice, however, the pre-defined priors are easily violated and the paired training data are hard to collect. To overcome these limitations, in this work, we propose RainRemoval-GAN (RRGAN), the first end-to-end adversarial model that generates realistic rain-free images using only unpaired supervision. Our approach alleviates the paired training constraints by introducing a physical-model which explicitly learns a recovered images and corresponding rain-streaks from the differentiable programming perspective. The proposed network consists of a novel multiscale attention memory generator and a novel multiscale deeply supervised discriminator. The multiscale attention memory generator uses a memory with attention mechanism to capture the latent rain streaks context at different stages to recover the clean images. The deeply supervised multiscale discriminator imposes constraints at the recovered output in terms of local details and global appearance to the clean image set. Together with the learned rainstreaks, a reconstruction constraint is employed to ensure the appearance consistent with the input image. Experimental results on public benchmark demonstrates our promising performance compared with nine state-of-the-art methods in terms of PSNR, SSIM, visual qualities and running time.
30
Bovens, Luc, and Wlodek Rabinowicz. "Bets on Hats: On Dutch Books Against Groups, Degrees of Belief as Betting Rates, and Group-Reflection." Episteme 8, no. 3 (October 2011): 281–300. http://dx.doi.org/10.3366/epi.2011.0022.
Повний текст джерелаАнотація:
AbstractThe Story of the Hats is a puzzle in social epistemology. It describes a situation in which a group of rational agents with common priors and common goals seems vulnerable to a Dutch book if they are exposed to different information and make decisions independently. Situations in which this happens involve violations of what might be called the Group-Reflection Principle. As it turns out, the Dutch book is flawed. It is based on the betting interpretation of the subjective probabilities, but ignores the fact that this interpretation disregards strategic considerations that might influence betting behavior. A lesson to be learned concerns the interpretation of probabilities in terms of fair bets and, more generally, the role of strategic considerations in epistemic contexts. Another lesson concerns Group-Reflection, which in its unrestricted form is highly counter-intuitive. We consider how this principle of social epistemology should be re-formulated so as to make it tenable.
31
Almulihi, Ahmed, Fahd Alharithi, Sami Bourouis, Roobaea Alroobaea, Yogesh Pawar, and Nizar Bouguila. "Oil Spill Detection in SAR Images Using Online Extended Variational Learning of Dirichlet Process Mixtures of Gamma Distributions." Remote Sensing 13, no. 15 (July 29, 2021): 2991. http://dx.doi.org/10.3390/rs13152991.
Повний текст джерелаАнотація:
In this paper, we propose a Dirichlet process (DP) mixture model of Gamma distributions, which is an extension of the finite Gamma mixture model to the infinite case. In particular, we propose a novel online nonparametric Bayesian analysis method based on the infinite Gamma mixture model where the determination of the number of clusters is bypassed via an infinite number of mixture components. The proposed model is learned via an online extended variational Bayesian inference approach in a flexible way where the priors of model’s parameters are selected appropriately and the posteriors are approximated effectively in a closed form. The online setting has the advantage to allow data instances to be treated in a sequential manner, which is more attractive than batch learning especially when dealing with massive and streaming data. We demonstrated the performance and merits of the proposed statistical framework with a challenging real-world application namely oil spill detection in synthetic aperture radar (SAR) images.
32
Kreutz-Delgado, Kenneth, Joseph F. Murray, Bhaskar D. Rao, Kjersti Engan, Te-Won Lee, and Terrence J. Sejnowski. "Dictionary Learning Algorithms for Sparse Representation." Neural Computation 15, no. 2 (February 1, 2003): 349–96. http://dx.doi.org/10.1162/089976603762552951.
Повний текст джерелаАнотація:
Algorithms for data-driven learning of domain-specific overcomplete dictionaries are developed to obtain maximum likelihood and maximum a posteriori dictionary estimates based on the use of Bayesian models with concave/Schur-concave (CSC) negative log priors. Such priors are appropriate for obtaining sparse representations of environmental signals within an appropriately chosen (environmentally matched) dictionary. The elements of the dictionary can be interpreted as concepts, features, or words capable of succinct expression of events encountered in the environment (the source of the measured signals). This is a generalization of vector quantization in that one is interested in a description involving a few dictionary entries (the proverbial “25 words or less”), but not necessarily as succinct as one entry. To learn an environmentally adapted dictionary capable of concise expression of signals generated by the environment, we develop algorithms that iterate between a representative set of sparse representations found by variants of FOCUSS and an update of the dictionary using these sparse representations. Experiments were performed using synthetic data and natural images. For complete dictionaries, we demonstrate that our algorithms have improved performance over other independent component analysis (ICA) methods, measured in terms of signal-to-noise ratios of separated sources. In the overcomplete case, we show that the true underlying dictionary and sparse sources can be accurately recovered. In tests with natural images, learned overcomplete dictionaries are shown to have higher coding efficiency than complete dictionaries; that is, images encoded with an overcomplete dictionary have both higher compression (fewer bits per pixel) and higher accuracy (lower mean square error).
33
Zhang, Xiuming, Pratul P. Srinivasan, Boyang Deng, Paul Debevec, William T. Freeman, and Jonathan T. Barron. "NeRFactor." ACM Transactions on Graphics 40, no. 6 (December 2021): 1–18. http://dx.doi.org/10.1145/3478513.3480496.
Повний текст джерелаАнотація:
We address the problem of recovering the shape and spatially-varying reflectance of an object from multi-view images (and their camera poses) of an object illuminated by one unknown lighting condition. This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties. The key to our approach, which we call Neural Radiance Factorization (NeRFactor), is to distill the volumetric geometry of a Neural Radiance Field (NeRF) [Mildenhall et al. 2020] representation of the object into a surface representation and then jointly refine the geometry while solving for the spatially-varying reflectance and environment lighting. Specifically, NeRFactor recovers 3D neural fields of surface normals, light visibility, albedo, and Bidirectional Reflectance Distribution Functions (BRDFs) without any supervision, using only a re-rendering loss, simple smoothness priors, and a data-driven BRDF prior learned from real-world BRDF measurements. By explicitly modeling light visibility, NeRFactor is able to separate shadows from albedo and synthesize realistic soft or hard shadows under arbitrary lighting conditions. NeRFactor is able to recover convincing 3D models for free-viewpoint relighting in this challenging and underconstrained capture setup for both synthetic and real scenes. Qualitative and quantitative experiments show that NeRFactor outperforms classic and deep learning-based state of the art across various tasks. Our videos, code, and data are available at people.csail.mit.edu/xiuming/projects/nerfactor/.
34
Li, Kang, Lequan Yu, Shujun Wang, and Pheng-Ann Heng. "Towards Cross-Modality Medical Image Segmentation with Online Mutual Knowledge Distillation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 775–83. http://dx.doi.org/10.1609/aaai.v34i01.5421.
Повний текст джерелаАнотація:
The success of deep convolutional neural networks is partially attributed to the massive amount of annotated training data. However, in practice, medical data annotations are usually expensive and time-consuming to be obtained. Considering multi-modality data with the same anatomic structures are widely available in clinic routine, in this paper, we aim to exploit the prior knowledge (e.g., shape priors) learned from one modality (aka., assistant modality) to improve the segmentation performance on another modality (aka., target modality) to make up annotation scarcity. To alleviate the learning difficulties caused by modality-specific appearance discrepancy, we first present an Image Alignment Module (IAM) to narrow the appearance gap between assistant and target modality data. We then propose a novel Mutual Knowledge Distillation (MKD) scheme to thoroughly exploit the modality-shared knowledge to facilitate the target-modality segmentation. To be specific, we formulate our framework as an integration of two individual segmentors. Each segmentor not only explicitly extracts one modality knowledge from corresponding annotations, but also implicitly explores another modality knowledge from its counterpart in mutual-guided manner. The ensemble of two segmentors would further integrate the knowledge from both modalities and generate reliable segmentation results on target modality. Experimental results on the public multi-class cardiac segmentation data, i.e., MM-WHS 2017, show that our method achieves large improvements on CT segmentation by utilizing additional MRI data and outperforms other state-of-the-art multi-modality learning methods.
35
Litwin, Piotr. "Extending Bayesian Models of the Rubber Hand Illusion." Multisensory Research 33, no. 2 (January 8, 2020): 127–60. http://dx.doi.org/10.1163/22134808-20191440.
Повний текст джерелаАнотація:
Abstract Human body sense is surprisingly flexible — in the Rubber Hand Illusion (RHI), precisely administered visuo-tactile stimulation elicits a sense of ownership over a fake hand. The general consensus is that there are certain semantic top-down constraints on which objects may be incorporated in this way: in particular, to-be-embodied objects should be structurally similar to a visual representation stored in an internal body model. However, empirical evidence shows that the sense of ownership may extend to objects strikingly distinct in morphology and structure (e.g., robotic arms) and the hypothesis about the relevance of appearance lacks direct empirical support. Probabilistic multisensory integration approaches constitute a promising alternative. However, the recent Bayesian models of RHI limit too strictly the possible factors influencing likelihood and prior probability distributions. In this paper, I analyse how Bayesian models of RHI could be extended. The introduction of skin-based spatial information can account for the cross-compensation of sensory signals giving rise to RHI. Furthermore, addition of Bayesian Coupling Priors, depending on (1) internal learned models of relatedness (coupling strength) of sensory cues, (2) scope of temporal binding windows, and (3) extension of peripersonal space, would allow quantification of individual tendencies to integrate divergent visual and somatosensory signals. The extension of Bayesian models would yield an empirically testable proposition accounting comprehensively for a wide spectrum of RHI-related phenomena and rendering appearance-oriented internal body models explanatorily redundant.
36
Wang, Chun. "On Interim Cognitive Diagnostic Computerized Adaptive Testing in Learning Context." Applied Psychological Measurement 45, no. 4 (February 23, 2021): 235–52. http://dx.doi.org/10.1177/0146621621990755.
Повний текст джерелаАнотація:
Interim assessment occurs throughout instruction to provide feedback about what students know and have achieved. Different from the current available cognitive diagnostic computerized adaptive testing (CD-CAT) design that focuses on assessment at a single time point, the authors discuss several designs of interim CD-CAT that are suitable in the learning context. The interim CD-CAT differs from the current available CD-CAT designs primarily because students’ mastery profile (i.e., skills mastery) changes due to learning, and new attributes are added periodically. Moreover, hierarchies exist among attributes taught sequentially and such information could be used during item selection. Two specific designs are considered: The first one is when new attributes are taught in Stage II, but the student mastery status of the previously taught attributes stays the same. The second design is when both new attributes are taught, and previously taught attributes can be further learned or forgotten in Stage II. For both designs, the authors propose an individual prior, which considers a person’s learning history and population learning model, to start an interim CD-CAT. Simulation results show that the Stage II CD-CAT using individual prior outperforms the methods using population priors. The GDINA (generalized deterministic inputs, noisy, “and” gate) diagnostic index (GDI) is extended to accommodate item hierarchies, and analytic results are provided to further illustrate the types of items that are most popular during item selection. As the first study that focuses on the application of CD-CAT in a learning context, the methods and results present herein showed the great promise of using CD-CAT to monitor learning.
37
Meaney, Christopher, Michael Escobar, Therese A. Stukel, Peter C. Austin, and Liisa Jaakkimainen. "Comparison of Methods for Estimating Temporal Topic Models From Primary Care Clinical Text Data: Retrospective Closed Cohort Study." JMIR Medical Informatics 10, no. 12 (December 19, 2022): e40102. http://dx.doi.org/10.2196/40102.
Повний текст джерелаАнотація:
Background Health care organizations are collecting increasing volumes of clinical text data. Topic models are a class of unsupervised machine learning algorithms for discovering latent thematic patterns in these large unstructured document collections. Objective We aimed to comparatively evaluate several methods for estimating temporal topic models using clinical notes obtained from primary care electronic medical records from Ontario, Canada. Methods We used a retrospective closed cohort design. The study spanned from January 01, 2011, through December 31, 2015, discretized into 20 quarterly periods. Patients were included in the study if they generated at least 1 primary care clinical note in each of the 20 quarterly periods. These patients represented a unique cohort of individuals engaging in high-frequency use of the primary care system. The following temporal topic modeling algorithms were fitted to the clinical note corpus: nonnegative matrix factorization, latent Dirichlet allocation, the structural topic model, and the BERTopic model. Results Temporal topic models consistently identified latent topical patterns in the clinical note corpus. The learned topical bases identified meaningful activities conducted by the primary health care system. Latent topics displaying near-constant temporal dynamics were consistently estimated across models (eg, pain, hypertension, diabetes, sleep, mood, anxiety, and depression). Several topics displayed predictable seasonal patterns over the study period (eg, respiratory disease and influenza immunization programs). Conclusions Nonnegative matrix factorization, latent Dirichlet allocation, structural topic model, and BERTopic are based on different underlying statistical frameworks (eg, linear algebra and optimization, Bayesian graphical models, and neural embeddings), require tuning unique hyperparameters (optimizers, priors, etc), and have distinct computational requirements (data structures, computational hardware, etc). Despite the heterogeneity in statistical methodology, the learned latent topical summarizations and their temporal evolution over the study period were consistently estimated. Temporal topic models represent an interesting class of models for characterizing and monitoring the primary health care system.
38
Zhu, Xuan, Xianxian Wang, Jun Wang, Peng Jin, Li Liu, and Dongfeng Mei. "Image Super-Resolution Based on Sparse Representation via Direction and Edge Dictionaries." Mathematical Problems in Engineering 2017 (2017): 1–11. http://dx.doi.org/10.1155/2017/3259357.
Повний текст джерелаАнотація:
Sparse representation has recently attracted enormous interests in the field of image super-resolution. The sparsity-based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super-resolution. For single-image super-resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize super-resolution. The above single-image super-resolution can restore the faithful high-frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super-resolution. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.
39
Do, Huy, Pascal Bourdon, David Helbert, Mathieu Naudin, and Remy Guillevin. "7T MRI super-resolution with Generative Adversarial Network." Electronic Imaging 2021, no. 18 (January 18, 2021): 106–1. http://dx.doi.org/10.2352/issn.2470-1173.2021.18.3dia-106.
Повний текст джерелаАнотація:
The high-resolution magnetic resonance image (MRI) provides detailed anatomical information critical for clinical application diagnosis. However, high-resolution MRI typically comes at the cost of long scan time, small spatial coverage, and low signal-to-noise ratio. The benefits of the convolutional neural network (CNN) can be applied to solve the super-resolution task to recover high-resolution generic images from low-resolution inputs. Additionally, recent studies have shown the potential to use the generative advertising network (GAN) to generate high-quality super-resolution MRIs using learned image priors. Moreover, existing approaches require paired MRI images as training data, which is difficult to obtain with existing datasets when the alignment between high and low-resolution images has to be implemented manually.This paper implements two different GAN-based models to handle the super-resolution: Enhanced super-resolution GAN (ESRGAN) and CycleGAN. Different from the generic model, the architecture of CycleGAN is modified to solve the super-resolution on unpaired MRI data, and the ESRGAN is implemented as a reference to compare GAN-based methods performance. The results of GAN-based models provide generated high-resolution images with rich textures compared to the ground-truth. Moreover, results from experiments are performed on both 3T and 7T MRI images in recovering different scales of resolution.
40
Hong, Fangzhou, Mingyuan Zhang, Liang Pan, Zhongang Cai, Lei Yang, and Ziwei Liu. "AvatarCLIP." ACM Transactions on Graphics 41, no. 4 (July 2022): 1–19. http://dx.doi.org/10.1145/3528223.3530094.
Повний текст джерелаАнотація:
3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability. Codes are available at https://github.com/hongfz16/AvatarCLIP.
41
Bellitto, G., F. Proietto Salanitri, S. Palazzo, F. Rundo, D. Giordano, and C. Spampinato. "Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction." International Journal of Computer Vision 129, no. 12 (October 5, 2021): 3216–32. http://dx.doi.org/10.1007/s11263-021-01519-y.
Повний текст джерелаАнотація:
AbstractIn this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different abstraction levels. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. For the former, we encourage the model to unsupervisedly learn hierarchical general features using gradient reversal at multiple scales, to enhance generalization capabilities on datasets for which no annotations are provided during training. As for domain specialization, we employ domain-specific operations (namely, priors, smoothing and batch normalization) by specializing the learned features on individual datasets in order to maximize performance. The results of our experiments show that the proposed model yields state-of-the-art accuracy on supervised saliency prediction. When the base hierarchical model is empowered with domain-specific modules, performance improves, outperforming state-of-the-art models on three out of five metrics on the DHF1K benchmark and reaching the second-best results on the other two. When, instead, we test it in an unsupervised domain adaptation setting, by enabling hierarchical gradient reversal layers, we obtain performance comparable to supervised state-of-the-art. Source code, trained models and example outputs are publicly available at https://github.com/perceivelab/hd2s.
42
Bellitto, G., F. Proietto Salanitri, S. Palazzo, F. Rundo, D. Giordano, and C. Spampinato. "Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction." International Journal of Computer Vision 129, no. 12 (October 5, 2021): 3216–32. http://dx.doi.org/10.1007/s11263-021-01519-y.
Повний текст джерелаАнотація:
AbstractIn this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different abstraction levels. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. For the former, we encourage the model to unsupervisedly learn hierarchical general features using gradient reversal at multiple scales, to enhance generalization capabilities on datasets for which no annotations are provided during training. As for domain specialization, we employ domain-specific operations (namely, priors, smoothing and batch normalization) by specializing the learned features on individual datasets in order to maximize performance. The results of our experiments show that the proposed model yields state-of-the-art accuracy on supervised saliency prediction. When the base hierarchical model is empowered with domain-specific modules, performance improves, outperforming state-of-the-art models on three out of five metrics on the DHF1K benchmark and reaching the second-best results on the other two. When, instead, we test it in an unsupervised domain adaptation setting, by enabling hierarchical gradient reversal layers, we obtain performance comparable to supervised state-of-the-art. Source code, trained models and example outputs are publicly available at https://github.com/perceivelab/hd2s.
43
Chagwiza, Conilius, Lillias Hamufari, and Gladys Sunzuma*. "Exploring Zimbabwean A-Level Mathematics Learners’ Understanding of the Determinant Concept." European Journal of Mathematics and Science Education 2, no. 2 (December 15, 2021): 85–100. http://dx.doi.org/10.12973/ejmse.2.2.85.
Повний текст джерелаАнотація:
<p style="text-align: justify;">Learners bring prior knowledge to their learning environments. This prior knowledge is said to have an effect on how they encode and later retrieve new information learned. This research aimed at exploring ‘A’ level mathematics learners’ understanding of the determinant concept of 3×3 matrices. A problem-solving approach was used to determine learners' conceptions and errors made in calculating the determinant. To identify the conceptions; a paper and pencil test, learner interviews, and learner questionnaires were used. Ten learners participated in the research and purposive sampling was used to select learners who are doing the syllabus 6042/2 Zimbabwe School Examination Council (ZIMSEC). Data was analyzed qualitatively through an analysis of each learners' problem-solving performance where common themes were identified amongst the learners’ work. Results from the themes showed that Advanced level learners faced some challenges in calculating the determinant of 3×3 matrices. Learners were having challenges with the place signs used in 3×3 matrices, especially when using the method of cofactors. The findings reveal that learners had low levels of engagement with the concepts and the abstract nature of the concepts was the major source of these challenges. The study recommends that; teachers should engage learners for lifelong learning and apply some mathematical definitions in real-world problems. Teachers should address the issues raised in this research during the teaching and learning process. In addition, teachers should engage learners more through seminars where learners get to mingle with others from other schools.</p>
44
Carter, Kimberlee, and Maria Camila Redondo Morant. "Co-Designing OER with Learners: A Replacement to Traditional College Level Assessments." Open/Technology in Education, Society, and Scholarship Association Conference 2, no. 1 (December 23, 2022): 1–5. http://dx.doi.org/10.18357/otessac.2022.2.1.110.
Повний текст джерелаАнотація:
Academic integrity issues in higher education have been reported as increasing as the pandemic and need to learn remotely continues. The use of homework sites like Chegg, that provide learners with answers to tests and assignments increased significantly through 2019 and 2020 (Walsh et al., 2021). Open advocates have been espousing the benefits of open educational resource assignments co-constructed with learners and published in the open prior to the pandemic. These have largely been writing assignments taking the form of blogs with a focus on teaching practices. An example of this phenomenon is the Open Learner Patchbook where learners write blog posts to share in the open (Open Education Global, 2019). A faculty involved in two projects that co-designed Open Education Resources (OER) with learners was curious to know what processes learned could be applied to co-designing OER assignments in their own teaching practice as an alternative to traditional assessments where answers can be found on homework sites. Easton et al. (2019) propose that original assignments encourage learners to complete their own work. This presentation focuses on what was learned in the co-design process with learners and what can be applied to teaching practices in college diploma and certificate courses.
45
Kaplan, Thomas, Jonathan Cannon, Lorenzo Jamone, and Marcus Pearce. "Modeling enculturated bias in entrainment to rhythmic patterns." PLOS Computational Biology 18, no. 9 (September 29, 2022): e1010579. http://dx.doi.org/10.1371/journal.pcbi.1010579.
Повний текст джерелаАнотація:
Long-term and culture-specific experience of music shapes rhythm perception, leading to enculturated expectations that make certain rhythms easier to track and more conducive to synchronized movement. However, the influence of enculturated bias on the moment-to-moment dynamics of rhythm tracking is not well understood. Recent modeling work has formulated entrainment to rhythms as a formal inference problem, where phase is continuously estimated based on precise event times and their correspondence to timing expectations: PIPPET (Phase Inference from Point Process Event Timing). Here we propose that the problem of optimally tracking a rhythm also requires an ongoing process of inferring which pattern of event timing expectations is most suitable to predict a stimulus rhythm. We formalize this insight as an extension of PIPPET called pPIPPET (PIPPET with pattern inference). The variational solution to this problem introduces terms representing the likelihood that a stimulus is based on a particular member of a set of event timing patterns, which we initialize according to culturally-learned prior expectations of a listener. We evaluate pPIPPET in three experiments. First, we demonstrate that pPIPPET can qualitatively reproduce enculturated bias observed in human tapping data for simple two-interval rhythms. Second, we simulate categorization of a continuous three-interval rhythm space by Western-trained musicians through derivation of a comprehensive set of priors for pPIPPET from metrical patterns in a sample of Western rhythms. Third, we simulate iterated reproduction of three-interval rhythms, and show that models configured with notated rhythms from different cultures exhibit both universal and enculturated biases as observed experimentally in listeners from those cultures. These results suggest the influence of enculturated timing expectations on human perceptual and motor entrainment can be understood as approximating optimal inference about the rhythmic stimulus, with respect to prototypical patterns in an empirical sample of rhythms that represent the music-cultural environment of the listener.
46
Zhang, Yupei, Yue Yun, Huan Dai, Jiaqi Cui, and Xuequn Shang. "Graphs Regularized Robust Matrix Factorization and Its Application on Student Grade Prediction." Applied Sciences 10, no. 5 (March 4, 2020): 1755. http://dx.doi.org/10.3390/app10051755.
Повний текст джерелаАнотація:
Student grade prediction (SGP) is an important educational problem for designing personalized strategies of teaching and learning. Many studies adopt the technique of matrix factorization (MF). However, their methods often focus on the grade records regardless of the side information, such as backgrounds and relationships. To this end, in this paper, we propose a new MF method, called graph regularized robust matrix factorization (GRMF), based on the recent robust MF version. GRMF integrates two side graphs built on the side data of students and courses into the objective of robust low-rank MF. As a result, the learned features of students and courses can grasp more priors from educational situations to achieve higher grade prediction results. The resulting objective problem can be effectively optimized by the Majorization Minimization (MM) algorithm. In addition, GRMF not only can yield the specific features for the education domain but can also deal with the case of missing, noisy, and corruptive data. To verify our method, we test GRMF on two public data sets for rating prediction and image recovery. Finally, we apply GRMF to educational data from our university, which is composed of 1325 students and 832 courses. The extensive experimental results manifestly show that GRMF is robust to various data problem and achieves more effective features in comparison with other methods. Moreover, GRMF also delivers higher prediction accuracy than other methods on our educational data set. This technique can facilitate personalized teaching and learning in higher education.
47
Zhang, Wenqiao, Haochen Shi, Siliang Tang, Jun Xiao, Qiang Yu, and Yueting Zhuang. "Consensus Graph Representation Learning for Better Grounded Image Captioning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 3394–402. http://dx.doi.org/10.1609/aaai.v35i4.16452.
Повний текст джерелаАнотація:
The contemporary visual captioning models frequently hallucinate objects that are not actually in a scene, due to the visual misclassification or over-reliance on priors that resulting in the semantic inconsistency between the visual information and the target lexical words. The most common way is to encourage the captioning model to dynamically link generated object words or phrases to appropriate regions of the image, i.e., the grounded image captioning (GIC). However, GIC utilizes an auxiliary task (grounding objects) that has not solved the key issue of object hallucination, i.e., the semantic inconsistency. In this paper, we take a novel perspective on the issue above: exploiting the semantic coherency between the visual and language modalities. Specifically, we propose the Consensus Rraph Representation Learning framework (CGRL) for GIC that incorporates a consensus representation into the grounded captioning pipeline. The consensus is learned by aligning the visual graph (e.g., scene graph) to the language graph that consider both the nodes and edges in a graph. With the aligned consensus, the captioning model can capture both the correct linguistic characteristics and visual relevance, and then grounding appropriate image regions further. We validate the effectiveness of our model, with a significant decline in object hallucination (-9% CHAIRi) on the Flickr30k Entities dataset. Besides, our CGRL also evaluated by several automatic metrics and human evaluation, the results indicate that the proposed approach can simultaneously improve the performance of image captioning (+2.9 Cider) and grounding (+2.3 F1LOC}).
48
Liu, Jiang, and Seth Wiener. "CFL learners’ Mandarin syllable-tone word production: effects of task and prior phonological and lexical learning." Chinese as a Second Language Research 10, no. 1 (March 30, 2021): 31–52. http://dx.doi.org/10.1515/caslar-2021-0002.
Повний текст джерелаАнотація:
Abstract This study examined beginner-level Chinese as a Foreign Language (CFL) learners’ production of newly learned words in an image naming and pinyin-reading task. Fifteen L1-English CFL learners learned 10 tonal monosyllabic minimal pairs (e.g., shu1 and shu3) in a three-day sound-image word learning experiment. Ten of the 20 words were homophonous with previously learned words (e.g., participants already knew that shu1 means ‘book’), while the other 10 were not (e.g., no shu3 words had been learned). Ten of the 20 words had frequent phonology participants were familiar with (e.g., shi is a high token frequency syllable), while the other 10 had infrequent phonology (e.g., ku is a low token frequency syllable). On the last day of learning, participants performed an image naming task followed by a pinyin-reading task. The recoded word tokens from both tasks were then played to 10 native Chinese speakers who were asked to transcribe the words in pinyin. The results showed that overall word production in the pinyin-reading task was more accurate than image naming. The pinyin-reading advantage was robust, but homophone status and syllable token frequency also interacted with task type: learners produced syllables with high token frequency but without homophones equally well in the pinyin-reading and naming tasks. These results suggest phonological encoding in long-term memory based on pinyin orthography can be affected by learners’ prior phonological and lexical knowledge. Pedagogical applications and limitations of the study are discussed, as well.
49
Chen, Yixuan, Shuang Wang, Fan Jiang, Yaxin Tu, and Qionghao Huang. "DCKT: A Novel Dual-Centric Learning Model for Knowledge Tracing." Sustainability 14, no. 23 (December 6, 2022): 16307. http://dx.doi.org/10.3390/su142316307.
Повний текст джерелаАнотація:
Knowledge tracing (KT), aiming to model learners’ mastery of a concept based on their historical learning records, has received extensive attention due to its great potential in realizing personalized learning in intelligent tutoring systems. However, most existing KT methods focus on a single aspect of knowledge or learner, not paying careful attention to the coupling influence of knowledge and learner characteristics. To fill this gap, in this paper, we explore a new paradigm for the KT task by exploiting the coupling influence of knowledge and learner. A novel model called Dual-Centric Knowledge Tracing (DCKT) is proposed to model knowledge states through two joint tasks of knowledge modeling and learner modeling. In particular, we first generate concept embeddings in abundant knowledge structure information via a pretext task (knowledge-centric): unsupervised graph representation learning. Then, we deeply measure learners’ prior knowledge the knowledge-enhanced representations and three predefined educational priors for discriminative feature enhancement. Furthermore, we design a forgetting-fusion transformer (learner-centric) to simulate the declining trend of learners’ knowledge proficiency over time, representing the common forgetting phenomenon. Extensive experiments were conducted on four public datasets, and the results demonstrate that DCKT could achieve better knowledge tracing results over all datasets via a dual-centric modeling process. Additionally, DCKT can learn meaningful question embeddings automatically without manual annotations. Our work indicates a potential future research direction for personalized learner modeling, which is of both accuracy and high interpretability.
50
Smith, Anne. "“You are contagious”: The Role of the Facilitator in Fostering Self-Efficacy in Learners." Scenario: A Journal of Performative Teaching, Learning, Research XI, no. 2 (July 1, 2017): 1–14. http://dx.doi.org/10.33178/scenario.11.2.1.
Повний текст джерелаАнотація:
This article argues that improvised role-play can raise learners’ levels of self-efficacy, which in turn increases their likelihood of using language learned beyond the workshop space. It argues that the physicality of the facilitator plays a key role in developing the self-efficacy of learners, using evidence drawn from the study of two Creative English groups with differing outcomes in terms of the use of English beyond the sessions.Creative English is a national, community-based applied theatre programme in the UK, which teaches adult migrants the English they need for everyday situations such as talking to doctors and landlords through drama. It works with those with low levels of English, including those who may have no prior experience of formal education.The article identifies kinaesthetic approaches to facilitating a learner in role, which help to lower the affective filter, and support learner progression in a mixed ability group. It examines the role the body plays in accelerating the creation of a supportive group dynamic, and where it can support and interfere with the likelihood of applying the language and confidence developed in real life.