Journal articles: 'Similarity metric learning'

1

Loriette, Antoine, Wanyu Liu, Frédéric Bevilacqua, and Baptiste Caramiaux. "Describing movement learning using metric learning." PLOS ONE 18, no. 2 (February 3, 2023): e0272509. http://dx.doi.org/10.1371/journal.pone.0272509.

Full text

Abstract:

Analysing movement learning can rely on human evaluation, e.g. annotating video recordings, or on computing means in applying metrics on behavioural data. However, it remains challenging to relate human perception of movement similarity to computational measures that aim at modelling such similarity. In this paper, we propose a metric learning method bridging the gap between human ratings of movement similarity in a motor learning task and computational metric evaluation on the same task. It applies metric learning on a Dynamic Time Warping algorithm to derive an optimal set of movement features that best explain human ratings. We evaluated this method on an existing movement dataset, which comprises videos of participants practising a complex gesture sequence toward a target template, as well as the collected data that describes the movements. We show that it is possible to establish a linear relationship between human ratings and our learned computational metric. This learned metric can be used to describe the most salient temporal moments implicitly used by annotators, as well as movement parameters that correlate with motor improvements in the dataset. We conclude with possibilities to generalise this method for designing computational tools dedicated to movement annotation and evaluation of skill learning.

APA, Harvard, Vancouver, ISO, and other styles

2

Tao, Tao, Qianqian Wang, Yue Ruan, Xue Li, and Xiujun Wang. "Graph Embedding with Similarity Metric Learning." Symmetry 15, no. 8 (August 21, 2023): 1618. http://dx.doi.org/10.3390/sym15081618.

Full text

Abstract:

Graph embedding transforms high-dimensional graphs into a lower-dimensional vector space while preserving their structural information and properties. Context-sensitive graph embedding, in particular, performs well in tasks such as link prediction and ranking recommendations. However, existing context-sensitive graph embeddings have limitations: they require additional information, depend on community algorithms to capture multiple contexts, or fail to capture sufficient structural information. In this paper, we propose a novel Graph Embedding with Similarity Metric Learning (GESML). The core of GESML is to learn the optimal graph structure using an attention-based symmetric similarity metric function and establish association relationships between nodes through top-k pooling. Its primary advantage lies in not requiring additional features or multiple contexts, only using the symmetric similarity metric function and pooling operations to encode sufficient topological information for each node. Experimental results on three datasets involving link prediction and node-clustering tasks demonstrate that GESML significantly improves learning for all challenging tasks relative to a state-of-the-art (SOTA) baseline.

APA, Harvard, Vancouver, ISO, and other styles

3

LE, Yi-ze, Yong FENG, Da-jiang LIU, and Bao-hua QIANG. "Adversarial Metric Learning with Naive Similarity Discriminator." IEICE Transactions on Information and Systems E103.D, no. 6 (June 1, 2020): 1406–13. http://dx.doi.org/10.1587/transinf.2019edp7278.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Li, Yujiang, Chun Ding, and Zhili Zhou. "Vehicle Matching Based on Similarity Metric Learning." Journal of New Media 4, no. 1 (2022): 51–58. http://dx.doi.org/10.32604/jnm.2022.028775.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Wei, Zeqiang, Min Xu, Lin Geng, Haoming Liu, and Hua Yin. "Adversarial Similarity Metric Learning for Kinship Verification." IEEE Access 7 (2019): 100029–35. http://dx.doi.org/10.1109/access.2019.2929939.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Cao, Qiong, Zheng-Chu Guo, and Yiming Ying. "Generalization bounds for metric and similarity learning." Machine Learning 102, no. 1 (June 20, 2015): 115–32. http://dx.doi.org/10.1007/s10994-015-5499-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Lowe, David G. "Similarity Metric Learning for a Variable-Kernel Classifier." Neural Computation 7, no. 1 (January 1995): 72–85. http://dx.doi.org/10.1162/neco.1995.7.1.72.

Full text

Abstract:

Nearest-neighbor interpolation algorithms have many useful properties for applications to learning, but they often exhibit poor generalization. In this paper, it is shown that much better generalization can be obtained by using a variable interpolation kernel in combination with conjugate gradient optimization of the similarity metric and kernel size. The resulting method is called variable-kernel similarity metric (VSM) learning. It has been tested on several standard classification data sets, and on these problems it shows better generalization than backpropagation and most other learning methods. The number of parameters that must be determined through optimization are orders of magnitude less than for backpropagation or radial basis function (RBF) networks, which may indicate that the method better captures the essential degrees of variation in learning. Other features of VSM learning are discussed that make it relevant to models for biological learning in the brain.

APA, Harvard, Vancouver, ISO, and other styles

8

Garcia, Noa, and George Vogiatzis. "Learning non-metric visual similarity for image retrieval." Image and Vision Computing 82 (February 2019): 18–25. http://dx.doi.org/10.1016/j.imavis.2019.01.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Wang, Huibing, Lin Feng, Jing Zhang, and Yang Liu. "Semantic Discriminative Metric Learning for Image Similarity Measurement." IEEE Transactions on Multimedia 18, no. 8 (August 2016): 1579–89. http://dx.doi.org/10.1109/tmm.2016.2569412.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Zhang, Lei, and David Zhang. "MetricFusion: Generalized metric swarm learning for similarity measure." Information Fusion 30 (July 2016): 80–90. http://dx.doi.org/10.1016/j.inffus.2015.12.004.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Kaya and Bilge. "Deep Metric Learning: A Survey." Symmetry 11, no. 9 (August 21, 2019): 1066. http://dx.doi.org/10.3390/sym11091066.

Full text

Abstract:

Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.

APA, Harvard, Vancouver, ISO, and other styles

12

Syed, Muhamamd Adnan, Zhenjun Han, Zhaoju Li, and Jianbin Jiao. "Impostor Resilient Multimodal Metric Learning for Person Reidentification." Advances in Multimedia 2018 (2018): 1–11. http://dx.doi.org/10.1155/2018/3202495.

Full text

Abstract:

In person reidentification distance metric learning suffers a great challenge from impostor persons. Mostly, distance metrics are learned by maximizing the similarity between positive pair against impostors that lie on different transform modals. In addition, these impostors are obtained from Gallery view for query sample only, while the Gallery sample is totally ignored. In real world, a given pair of query and Gallery experience different changes in pose, viewpoint, and lighting. Thus, impostors only from Gallery view can not optimally maximize their similarity. Therefore, to resolve these issues we have proposed an impostor resilient multimodal metric (IRM3). IRM3 is learned for each modal transform in the image space and uses impostors from both Probe and Gallery views to effectively restrict large number of impostors. Learned IRM3 is then evaluated on three benchmark datasets, VIPeR, CUHK01, and CUHK03, and shows significant improvement in performance compared to many previous approaches.

APA, Harvard, Vancouver, ISO, and other styles

13

Mishra, Hare Krishna, and Manpreet Kaur. "An Approach for Enhancement of MR Images of Brain Tumor." Traitement du Signal 39, no. 4 (August 31, 2022): 1133–44. http://dx.doi.org/10.18280/ts.390405.

Full text

Abstract:

Magnetic Resonance Imaging plays an important role in diagnosing the brain tumor accurately, but it requires the approach to enhance the magnetic resonance images to assist physicians in brain tumor detection and making the treatment plan precisely to reduce the mortality rate. Therefore, in this proposed work, a comprehensive learning-based elephant herding optimization technique has been introduced to select the optimal value of smoothness factor in Bi-Histogram Equalization with Adaptive Sigmoid Function that enhances the visual quality as well as the appearance of the suspicious regions in magnetic resonance images. Further, the enhancement performance has been evaluated by the enhancement quality metrics. The metrics used include mean square error, peak signal to noise ratio, mean absolute error, structural similarity index metric, feature similarity index metric, Riesz transformed based feature similarity index metric, spectral residual-based similarity index metric, and absolute mean brightness error. The outcomes of this proposed work have a remarkable impact on enhancing magnetic resonance images and providing visual assistance for diagnosing brain tumors. The performance of the evaluation metrics is verified with Friedman's mean rank test, which strongly indicates a statistical difference between the proposed method and state-of-the-art methods.

APA, Harvard, Vancouver, ISO, and other styles

14

Fan, Lili, Hongwei Zhao, Haoyu Zhao, Pingping Liu, and Huangshui Hu. "Distribution Structure Learning Loss (DSLL) Based on Deep Metric Learning for Image Retrieval." Entropy 21, no. 11 (November 15, 2019): 1121. http://dx.doi.org/10.3390/e21111121.

Full text

Abstract:

The massive number of images demands highly efficient image retrieval tools. Deep distance metric learning (DDML) is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, which has achieved encouraging results. The loss function is crucial in DDML frameworks. However, we found limitations to this model. When learning the similarity of positive and negative examples, the current methods aim to pull positive pairs as close as possible and separate negative pairs into equal distances in the embedding space. Consequently, the data distribution might be omitted. In this work, we focus on the distribution structure learning loss (DSLL) algorithm that aims to preserve the geometric information of images. To achieve this, we firstly propose a metric distance learning for highly matching figures to preserve the similarity structure inside it. Second, we introduce an entropy weight-based structural distribution to set the weight of the representative negative samples. Third, we incorporate their weights into the process of learning to rank. So, the negative samples can preserve the consistency of their structural distribution. Generally, we display comprehensive experimental results drawing on three popular landmark building datasets and demonstrate that our method achieves state-of-the-art performance.

APA, Harvard, Vancouver, ISO, and other styles

15

Brockmeier, Austin J., John S. Choi, Evan G. Kriminger, Joseph T. Francis, and Jose C. Principe. "Neural Decoding with Kernel-Based Metric Learning." Neural Computation 26, no. 6 (June 2014): 1080–107. http://dx.doi.org/10.1162/neco_a_00591.

Full text

Abstract:

In studies of the nervous system, the choice of metric for the neural responses is a pivotal assumption. For instance, a well-suited distance metric enables us to gauge the similarity of neural responses to various stimuli and assess the variability of responses to a repeated stimulus—exploratory steps in understanding how the stimuli are encoded neurally. Here we introduce an approach where the metric is tuned for a particular neural decoding task. Neural spike train metrics have been used to quantify the information content carried by the timing of action potentials. While a number of metrics for individual neurons exist, a method to optimally combine single-neuron metrics into multineuron, or population-based, metrics is lacking. We pose the problem of optimizing multineuron metrics and other metrics using centered alignment, a kernel-based dependence measure. The approach is demonstrated on invasively recorded neural data consisting of both spike trains and local field potentials. The experimental paradigm consists of decoding the location of tactile stimulation on the forepaws of anesthetized rats. We show that the optimized metrics highlight the distinguishing dimensions of the neural response, significantly increase the decoding accuracy, and improve nonlinear dimensionality reduction methods for exploratory neural analysis.

APA, Harvard, Vancouver, ISO, and other styles

16

Qiu, Wei. "Based on Semi-Supervised Clustering with the Boost Similarity Metric Method for Face Retrieval." Applied Mechanics and Materials 543-547 (March 2014): 2720–23. http://dx.doi.org/10.4028/www.scientific.net/amm.543-547.2720.

Full text

Abstract:

The focus of this paper is on Metric Learning, with particular interest in incorporating side information to make it semi-supervised. This study is primarily motivated by an application: face-image clustering. In the paper introduces metric learning and semi-supervised clustering, Boost the similarity metric learning method that adapt the underlying similarity metric used by the clustering algorithm. we propose a novel idea of learning with historical relevance feedback log data, and adopt a new paradigm called Boost the Similarity Metric Method for Face Retrieval, Experimental results demonstrate that the unified approach produces better clusters than both individual approaches as well as previously proposed semi-supervised clustering algorithms. This paper followed by the discussion of experiments on face-image clustering.

APA, Harvard, Vancouver, ISO, and other styles

17

Guo, Zheng-Chu, and Yiming Ying. "Guaranteed Classification via Regularized Similarity Learning." Neural Computation 26, no. 3 (March 2014): 497–522. http://dx.doi.org/10.1162/neco_a_00556.

Full text

Abstract:

Learning an appropriate (dis)similarity function from the available data is a central problem in machine learning, since the success of many machine learning algorithms critically depends on the choice of a similarity function to compare examples. Despite many approaches to similarity metric learning that have been proposed, there has been little theoretical study on the links between similarity metric learning and the classification performance of the resulting classifier. In this letter, we propose a regularized similarity learning formulation associated with general matrix norms and establish their generalization bounds. We show that the generalization error of the resulting linear classifier can be bounded by the derived generalization bound of similarity learning. This shows that a good generalization of the learned similarity function guarantees a good classification of the resulting linear classifier. Our results extend and improve those obtained by Bellet, Habrard, and Sebban ( 2012 ). Due to the techniques dependent on the notion of uniform stability (Bousquet & Elisseeff, 2002 ), the bound obtained there holds true only for the Frobenius matrix-norm regularization. Our techniques using the Rademacher complexity (Bartlett & Mendelson, 2002 ) and its related Khinchin-type inequality enable us to establish bounds for regularized similarity learning formulations associated with general matrix norms, including sparse L1-norm and mixed (2,1)-norm.

APA, Harvard, Vancouver, ISO, and other styles

18

Wang, Hang, and Duanbing Chen. "Few-Shot Image Classification Based on Ensemble Metric Learning." Journal of Physics: Conference Series 2171, no. 1 (January 1, 2022): 012027. http://dx.doi.org/10.1088/1742-6596/2171/1/012027.

Full text

Abstract:

Abstract In the case of few labelled image data samples, image classification is a difficult challenge, which is called few-shot image classification. Recently, many methods based on metric learning have been proposed. Most of these methods mainly focus on the representations of global image-level features or local feature-level descriptors. However, these methods calculate similarity from a single metric learning perspective. Motivated by ensemble learning, a novel Ensemble Metric Learning (EML) method for few-shot image classification is proposed, which not only utilizes label propagation, but also considers image-level and local feature-level descriptor metrics. The experimental results show that the proposed method can effectively improve the classification accuracy by ensemble learning.

APA, Harvard, Vancouver, ISO, and other styles

19

Wu, Bowen, and Huaming Wu. "Scalable Similarity-Consistent Deep Metric Learning for Face Recognition." IEEE Access 7 (2019): 104759–68. http://dx.doi.org/10.1109/access.2019.2931913.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Qi, Jinwei, Xin Huang, and Yuxin Peng. "Cross-media similarity metric learning with unified deep networks." Multimedia Tools and Applications 76, no. 23 (May 6, 2017): 25109–27. http://dx.doi.org/10.1007/s11042-017-4726-6.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Furuya, Takahiko, and Ryutarou Ohbuchi. "Similarity metric learning for sketch-based 3D object retrieval." Multimedia Tools and Applications 74, no. 23 (July 2, 2014): 10367–92. http://dx.doi.org/10.1007/s11042-014-2171-3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Zhao, Yan-Guo, Zhan Song, Feng Zheng, and Ling Shao. "Learning a Multiple Kernel Similarity Metric for kinship verification." Information Sciences 430-431 (March 2018): 247–60. http://dx.doi.org/10.1016/j.ins.2017.11.048.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Abualhaj, Mosleh M., Ahmad Adel Abu-Shareha, Qusai Y. Shambour, Adeeb Alsaaidah, Sumaya N. Al-Khatib, and Mohammed Anbar. "Customized K-nearest neighbors’ algorithm for malware detection." International Journal of Data and Network Science 8, no. 1 (2024): 431–38. http://dx.doi.org/10.5267/j.ijdns.2023.9.012.

Full text

Abstract:

The security and integrity of computer systems and networks highly depend on malware detection. In the realm of malware detection, the K-Nearest Neighbors (KNN) algorithm is a well-liked and successful machine learning algorithm. However, the choice of an acceptable distance metric parameter has a significant impact on the KNN algorithm's performance. This study tries to improve malware detection by adjusting the KNN algorithm's distance metric parameter. The distance metric greatly influences the similarity or dissimilarity between instances in the feature space. The KNN algorithm for malware detection can be more accurate and effective by carefully choosing or modifying the distance metric. This paper analyzes multiple distance metrics, including Minkowski distance, Manhattan distance, and Euclidean distance. These metrics account for the traits of malware samples while capturing various aspects of similarity. The effectiveness of the KNN algorithm is evaluated using the MalMem-2022 malware dataset, and the results are broken down into these three-distance metrics. The experimental findings show that, among the three distance metric parameters, the Euclidean and Minkowski distance metric parameters considerably produced the best outcomes with binary classification. While with multiclass classification, the KNN algorithm has achieved the highest outcomes using Manhattan distance.

APA, Harvard, Vancouver, ISO, and other styles

24

AYDIN, Fatih. "Uzaklık Metriklerinin Performansı Üzerine Ampirik Bir Çalışma." Afyon Kocatepe University Journal of Sciences and Engineering 23, no. 6 (December 22, 2023): 1445–57. http://dx.doi.org/10.35414/akufemubid.1325843.

Full text

Abstract:

Metrics are used to measure the distance, similarity, or dissimilarity between two points in a metric space. Metric learning algorithms perform the finding task of data points that are closest or furthest to a query point in m-dimensional metric space. Some metrics take into account the assumption that the whole dimensions are of equal importance, and vice versa. However, this assumption does not incorporate a number of real-world problems that classification algorithms tackle. In this research, the existing information gain, the information gain ratio, and some well-known conventional metrics have been compared by each other. The 1-Nearest Neighbor algorithm taking these metrics as its meta-parameter has been applied to forty-nine benchmark datasets. Only the accuracy rate criterion has been employed in order to quantify the performance of the metrics. The experimental results show that each metric is successful on datasets corresponding to its own domain. In other words, each metric is favorable on datasets overlapping its own assumption. In addition, there also exists incompleteness in classification tasks for metrics just like there is for learning algorithms.

APA, Harvard, Vancouver, ISO, and other styles

25

Xu, Yesong, Shuo Chen, Jun Li, and Jianjun Qian. "Linearity-Aware Subspace Clustering." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (June 28, 2022): 8770–78. http://dx.doi.org/10.1609/aaai.v36i8.20857.

Full text

Abstract:

Obtaining a good similarity matrix is extremely important in subspace clustering. Current state-of-the-art methods learn the similarity matrix through self-expressive strategy. However, these methods directly adopt original samples as a set of basis to represent itself linearly. It is difficult to accurately describe the linear relation between samples in the real-world applications, and thus is hard to find an ideal similarity matrix. To better represent the linear relation of samples, we present a subspace clustering model, Linearity-Aware Subspace Clustering (LASC), which can consciously learn the similarity matrix by employing a linearity-aware metric. This is a new subspace clustering method that combines metric learning and subspace clustering into a joint learning framework. In our model, we first utilize the self-expressive strategy to obtain an initial subspace structure and discover a low-dimensional representation of the original data. Subsequently, we use the proposed metric to learn an intrinsic similarity matrix with linearity-aware on the obtained subspace. Based on such a learned similarity matrix, the inter-cluster distance becomes larger than the intra-cluster distances, and thus successfully obtaining a good subspace cluster result. In addition, to enrich the similarity matrix with more consistent knowledge, we adopt a collaborative learning strategy for self-expressive subspace learning and linearity-aware subspace learning. Moreover, we provide detailed mathematical analysis to show that the metric can properly characterize the linear correlation between samples.

APA, Harvard, Vancouver, ISO, and other styles

26

Ma, Guixiang, Nesreen K. Ahmed, Theodore L. Willke, and Philip S. Yu. "Deep graph similarity learning: a survey." Data Mining and Knowledge Discovery 35, no. 3 (March 24, 2021): 688–725. http://dx.doi.org/10.1007/s10618-020-00733-5.

Full text

Abstract:

AbstractIn many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space. Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications. Finally, we discuss the challenges and future directions for this problem.

APA, Harvard, Vancouver, ISO, and other styles

27

Bahrami, Saeedeh, Alireza Bosaghzadeh, and Fadi Dornaika. "Multi Similarity Metric Fusion in Graph-Based Semi-Supervised Learning." Computation 7, no. 1 (March 7, 2019): 15. http://dx.doi.org/10.3390/computation7010015.

Full text

Abstract:

In semi-supervised label propagation (LP), the data manifold is approximated by a graph, which is considered as a similarity metric. Graph estimation is a crucial task, as it affects the further processes applied on the graph (e.g., LP, classification). As our knowledge of data is limited, a single approximation cannot easily find the appropriate graph, so in line with this, multiple graphs are constructed. Recently, multi-metric fusion techniques have been used to construct more accurate graphs which better represent the data manifold and, hence, improve the performance of LP. However, most of these algorithms disregard use of the information of label space in the LP process. In this article, we propose a new multi-metric graph-fusion method, based on the Flexible Manifold Embedding algorithm. Our proposed method represents a unified framework that merges two phases: graph fusion and LP. Based on one available view, different simple graphs were efficiently generated and used as input to our proposed fusion approach. Moreover, our method incorporated the label space information as a new form of graph, namely the Correlation Graph, with other similarity graphs. Furthermore, it updated the correlation graph to find a better representation of the data manifold. Our experimental results on four face datasets in face recognition demonstrated the superiority of the proposed method compared to other state-of-the-art algorithms.

APA, Harvard, Vancouver, ISO, and other styles

28

Hua, Keru, Qin Yu, and Ruiming Zhang. "A Guaranteed Similarity Metric Learning Framework for Biological Sequence Comparison." IEEE/ACM Transactions on Computational Biology and Bioinformatics 13, no. 5 (September 1, 2016): 868–77. http://dx.doi.org/10.1109/tcbb.2015.2495186.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Al-Halah, Ziad, Lukas Rybok, and Rainer Stiefelhagen. "Transfer metric learning for action similarity using high-level semantics." Pattern Recognition Letters 72 (March 2016): 82–90. http://dx.doi.org/10.1016/j.patrec.2015.07.005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Hou, Xiao-Nan, Shou-Hong Ding, Li-Zhuang Ma, Cheng-Jie Wang, Ji-Lin Li, and Fei-Yue Huang. "Similarity metric learning for face verification using sigmoid decision function." Visual Computer 32, no. 4 (April 2, 2015): 479–90. http://dx.doi.org/10.1007/s00371-015-1079-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Gundogdu, Batuhan, and Michael J. Bianco. "Collaborative similarity metric learning for face recognition in the wild." IET Image Processing 14, no. 9 (July 20, 2020): 1759–68. http://dx.doi.org/10.1049/iet-ipr.2019.0510.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Haskins, Grant, Jochen Kruecker, Uwe Kruger, Sheng Xu, Peter A. Pinto, Brad J. Wood, and Pingkun Yan. "Learning deep similarity metric for 3D MR–TRUS image registration." International Journal of Computer Assisted Radiology and Surgery 14, no. 3 (October 31, 2018): 417–25. http://dx.doi.org/10.1007/s11548-018-1875-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Rao, Qiyu. "Research of Metric Learning-Based Method for Person Re-Identification by Intelligent Computer Vision Technology." Journal of Physics: Conference Series 2083, no. 4 (November 1, 2021): 042013. http://dx.doi.org/10.1088/1742-6596/2083/4/042013.

Full text

Abstract:

Abstract Person re-identification technology aims to establish an efficient metric model for similarity distance measurement of pedestrian images. Candidate images captured by different camera views are ranked according to their similarities to the target individual. However, the metric learning-based method, which is commonly used in similarity measurement, often failed in person re-identification tasks due to the drastic variations in appearance. The main reason for its low identification accuracy is that the metric learning method is over-fitting to the training data. Several types of metric learning methods which differ from each other by the distribution of sample pairs were summarized in this article for analysing and easing the metric learning methods’ over-fitting problem. Three different metric learning methods were tested on the VIPeR dataset. The distributions of the distance of the positive/negative training/test pairs are displayed to demonstrate the over-fitting problem. Then, a new metric model was proposed by combining the thoughts of binary classification and multi-class classification. Related verification experiments were conducted on VIPeR dataset. Besides, the semi-supervised metric learning approach was introduced to alleviate the over-fitting problem. The experimental results reflect gap between training pairs and test pairs in the metric subspace. Therefore, reducing the difference between training data and test data is a promising way to improve the identification accuracy of metric learning method.

APA, Harvard, Vancouver, ISO, and other styles

34

Jawanpuria, Pratik, Arjun Balgovind, Anoop Kunchukuttan, and Bamdev Mishra. "Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach." Transactions of the Association for Computational Linguistics 7 (November 2019): 107–20. http://dx.doi.org/10.1162/tacl_a_00257.

Full text

Abstract:

We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples the source-to-target language transformation into (a) language-specific rotations on the original embeddings to align them in a common, latent space, and (b) a language-independent similarity metric in this common space to better model the similarity between the embeddings. Overall, we pose the bilingual mapping problem as a classification problem on smooth Riemannian manifolds. Empirically, our approach outperforms previous approaches on the bilingual lexicon induction and cross-lingual word similarity tasks. We next generalize our framework to represent multiple languages in a common latent space. Language-specific rotations for all the languages and a common similarity metric in the latent space are learned jointly from bilingual dictionaries for multiple language pairs. We illustrate the effectiveness of joint learning for multiple languages in an indirect word translation setting.

APA, Harvard, Vancouver, ISO, and other styles

35

Zhang, La, Haiyun Guo, Kuan Zhu, Honglin Qiao, Gaopan Huang, Sen Zhang, Huichen Zhang, Jian Sun, and Jinqiao Wang. "Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification." ACM Transactions on Multimedia Computing, Communications, and Applications 18, no. 1s (February 28, 2022): 1–15. http://dx.doi.org/10.1145/3473341.

Full text

Abstract:

Visible-infrared person re-identification (Re-ID) has received increasing research attention for its great practical value in night-time surveillance scenarios. Due to the large variations in person pose, viewpoint, and occlusion in the same modality, as well as the domain gap brought by heterogeneous modality, this hybrid modality person matching task is quite challenging. Different from the metric learning methods for visible person re-ID, which only pose similarity constraints on class level, an efficient metric learning approach for visible-infrared person Re-ID should take both the class-level and modality-level similarity constraints into full consideration to learn sufficiently discriminative and robust features. In this article, the hybrid modality is divided into two types, within modality and cross modality. We first fully explore the variations that hinder the ranking results of visible-infrared person re-ID and roughly summarize them into three types: within-modality variation, cross-modality modality-related variation, and cross-modality modality-unrelated variation. Then, we propose a comprehensive metric learning framework based on four kinds of paired-based similarity constraints to address all the variations within and cross modality. This framework focuses on both class-level and modality-level similarity relationships between person images. Furthermore, we demonstrate the compatibility of our framework with any paired-based loss functions by giving detailed implementation of combing it with triplet loss and contrastive loss separately. Finally, extensive experiments of our approach on SYSU-MM01 and RegDB demonstrate the effectiveness and superiority of our proposed metric learning framework for visible-infrared person Re-ID.

APA, Harvard, Vancouver, ISO, and other styles

36

Tang, HongZhong, Xiao Li, Xiang Wang, Lizhen Mao, and Ling Zhu. "Unsupervised feature learning via prior information‐based similarity metric learning for face verification." IET Signal Processing 12, no. 8 (October 2018): 966–74. http://dx.doi.org/10.1049/iet-spr.2017.0017.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Bashi, D., and S. Zucker. "Quantifying the similarity of planetary system architectures." Astronomy & Astrophysics 651 (July 2021): A61. http://dx.doi.org/10.1051/0004-6361/202140699.

Full text

Abstract:

The planetary systems detected so far exhibit a wide diversity of architectures, and various methods have been proposed to quantitatively study this diversity. Straightforward ways to quantify the difference between two systems, and more generally two sets of multi-planetary systems, are helpful for studying this diversity. In this work we present a novel approach, using a weighted extension of the energy distance (WED) metric, to quantify the difference between planetary systems on the logarithmic period-radius plane. We demonstrate the use of this metric and its relation to previously introduced descriptive measures to characterise the arrangements of Kepler planetary systems. By applying exploratory machine-learning tools, we attempt to find whether there is some order that can be ascribed to the set of multi-planet Kepler system architectures. Based on the WED, the ‘Sequencer’, which is such an automatic tool, identifies a progression from small and compact planetary systems to systems with distant giant planets. It is reassuring to see that a WED-based tool does indeed identify this progression. Next, we extend the WED to define the inter-catalogue energy distance – a distance metric between sets of multi-planetary systems. We have made the specific implementation presented in the paper available to the community through a public repository. We suggest using these metrics as complementary tools in attempts to compare different architectures of planetary systems and, in general, different catalogues of planetary systems.

APA, Harvard, Vancouver, ISO, and other styles

38

Wang, Qianying, Ming Lu, Meng Li, and Fei Guan. "Regularized Semi-Supervised Metric Learning with Latent Structure Preserved." International Journal of Computational Intelligence and Applications 20, no. 02 (June 2021): 2150013. http://dx.doi.org/10.1142/s1469026821500139.

Full text

Abstract:

Metric learning is a critical problem in classification. Most classifiers are based on a metric, the simplest one is the KNN classifier, whose outcome is directly decided by the given metric. This paper will discuss semi-supervised metric learning. Most traditional semi-supervised metric learning algorithms preserve the local structure of all the samples (including labeled and unlabeled) in the input space, when making the same labeled samples together and separating different labeled samples. In most existing methods, the local structure is calculated by the Euclidean distance which uses all the features. As we all know, high dimensional data lies on a low dimension manifold, and not all the features are discriminative. Thus, in this paper, we try to explore the latent structure of the samples and use the more discriminative features to calculate the local structure. The latent structure is learned by clustering random forest and cast into similarity between samples. Based on the hierarchical structure of the trees and the split function, the similarity is obtained from discriminant features. Experimental results on public data sets show our algorithm outperforms the traditional similar related algorithms.

APA, Harvard, Vancouver, ISO, and other styles

39

Wan, Zhijing, Zhixiang Wang, Yuran Wang, Zheng Wang, Hongyuan Zhu, and Shin'ichi Satoh. "Contributing Dimension Structure of Deep Feature for Coreset Selection." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 8 (March 24, 2024): 9080–88. http://dx.doi.org/10.1609/aaai.v38i8.28758.

Full text

Abstract:

Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a sample's representation in enhancing performance and the role of sample diversity in averting overfitting. Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm. They have capably tackled representation via distribution matching guided by the similarities of features, gradients, or other information between data. However, the results of effectively diverse sample selection are mired in sub-optimality. This is because the similarity metrics usually simply aggregate dimension similarities without acknowledging disparities among the dimensions that significantly contribute to the final similarity. As a result, they fall short of adequately capturing diversity. To address this, we propose a feature-based diversity constraint, compelling the chosen subset to exhibit maximum diversity. Our key lies in the introduction of a novel Contributing Dimension Structure (CDS) metric. Different from similarity metrics that measure the overall similarity of high-dimensional features, our CDS metric considers not only the reduction of redundancy in feature dimensions, but also the difference between dimensions that contribute significantly to the final similarity. We reveal that existing methods tend to favor samples with similar CDS, leading to a reduced variety of CDS types within the coreset and subsequently hindering model performance. In response, we enhance the performance of five classical selection methods by integrating the CDS constraint. Our experiments on three datasets demonstrate the general effectiveness of the proposed method in boosting existing methods.

APA, Harvard, Vancouver, ISO, and other styles

40

Gu, Geonmo, and Byungsoo Ko. "Symmetrical Synthesis for Deep Metric Learning." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 10853–60. http://dx.doi.org/10.1609/aaai.v34i07.6716.

Full text

Abstract:

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard sample generation are adopting autoencoders or generative adversarial networks, but this leads to more hyper-parameters, harder optimization, and slower training speed. In this paper, we address these problems by proposing a novel method of synthetic hard sample generation called symmetrical synthesis. Given two original feature points from the same class, the proposed method firstly generates synthetic points with each other as an axis of symmetry. Secondly, it performs hard negative pair mining within the original and synthetic points to select a more informative negative pair for computing the metric learning loss. Our proposed method is hyper-parameter free and plug-and-play for existing metric learning losses without network modification. We demonstrate the superiority of our proposed method over existing methods for a variety of loss functions on clustering and image retrieval tasks.

APA, Harvard, Vancouver, ISO, and other styles

41

Li, Ruifan, Fangxiang Feng, Xiaojie Wang, Peng Lu, and Bohan Li. "Obtaining Cross Modal Similarity Metric with Deep Neural Architecture." Mathematical Problems in Engineering 2015 (2015): 1–9. http://dx.doi.org/10.1155/2015/293176.

Full text

Abstract:

Analyzing complex system with multimodal data, such as image and text, has recently received tremendous attention. Modeling the relationship between different modalities is the key to address this problem. Motivated by recent successful applications of deep neural learning in unimodal data, in this paper, we propose a computational deep neural architecture, bimodal deep architecture (BDA) for measuring the similarity between different modalities. Our proposed BDA architecture has three closely related consecutive components. For image and text modalities, the first component can be constructed using some popular feature extraction methods in their individual modalities. The second component has two types of stacked restricted Boltzmann machines (RBMs). Specifically, for image modality a binary-binary RBM is stacked over a Gaussian-binary RBM; for text modality a binary-binary RBM is stacked over a replicated softmax RBM. In the third component, we come up with a variant autoencoder with a predefined loss function for discriminatively learning the regularity between different modalities. We show experimentally the effectiveness of our approach to the task of classifying image tags on public available datasets.

APA, Harvard, Vancouver, ISO, and other styles

42

Okarma, Krzysztof. "Current Trends and Advances in Image Quality Assessment." Elektronika ir Elektrotechnika 25, no. 3 (June 25, 2019): 77–84. http://dx.doi.org/10.5755/j01.eie.25.3.23681.

Full text

Abstract:

Image quality assessment (IQA) is one of the constantly active areas of research in computer vision. Starting from the idea of Universal Image Quality Index (UIQI), followed by well-known Structural Similarity (SSIM) and its numerous extensions and modifications, through Feature Similarity (FSIM) towards combined metrics using the multi-metric fusion approach, the development of image quality assessment is still in progress. Nevertheless, regardless of new databases and the potential use of deep learning methods, some challenges remain still up to date. Some of the IQA metrics can also be used efficiently for alternative purposes, such as texture similarity estimation, quality evaluation of 3D images and 3D printed surfaces as well as video quality assessment.

APA, Harvard, Vancouver, ISO, and other styles

43

Wang, Huibing, Lin Feng, Xiangzhu Meng, Zhaofeng Chen, Laihang Yu, and Hongwei Zhang. "Multi-view metric learning based on KL-divergence for similarity measurement." Neurocomputing 238 (May 2017): 269–76. http://dx.doi.org/10.1016/j.neucom.2017.01.062.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Zhou, Xiuzhuang, Kai Jin, Min Xu, and Guodong Guo. "Learning deep compact similarity metric for kinship verification from face images." Information Fusion 48 (August 2019): 84–94. http://dx.doi.org/10.1016/j.inffus.2018.07.011.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Prabhala, Jagat Chaitanya, Venkatnareshbabu K, and Ragoju Ravi. "OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIARIZATION SYSTEMS: A MATHEMATICAL FORMULATION." Applied Mathematics and Sciences An International Journal (MathSJ) 10, no. 1/2 (June 26, 2023): 1–10. http://dx.doi.org/10.5121/mathsj.2023.10201.

Full text

Abstract:

Speaker diarization is a critical task in speech processing that aims to identify "who spoke when?" in an audio or video recording that contains unknown amounts of speech from unknown speakers and unknown number of speakers. Diarization has numerous applications in speech recognition, speaker identification, and automatic captioning. Supervised and unsupervised algorithms are used to address speaker diarization problems, but providing exhaustive labeling for the training dataset can become costly in supervised learning, while accuracy can be compromised when using unsupervised approaches. This paper presents a novel approach to speaker diarization, which defines loosely labeled data and employs x-vector embedding and a formalized approach for threshold searching with a given abstract similarity metric to cluster temporal segments into unique user segments. The proposed algorithm uses concepts of graph theory, matrix algebra, and genetic algorithm to formulate and solve the optimization problem. Additionally, the algorithm is applied to English, Spanish, and Chinese audios, and the performance is evaluated using wellknown similarity metrics. The results demonstrate that the robustness of the proposed approach. The findings of this research have significant implications for speech processing, speaker identification including those with tonal differences. The proposed method offers a practical and efficient solution for speaker diarization in real-world scenarios where there are labeling time and cost constraints

APA, Harvard, Vancouver, ISO, and other styles

46

Liu, Wei, Xinmei Tian, Dacheng Tao, and Jianzhuang Liu. "Constrained Metric Learning Via Distance Gap Maximization." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (July 3, 2010): 518–24. http://dx.doi.org/10.1609/aaai.v24i1.7701.

Full text

Abstract:

Vectored data frequently occur in a variety of fields, which are easy to handle since they can be mathematically abstracted as points residing in a Euclidean space. An appropriate distance metric in the data space is quite demanding for a great number of applications. In this paper, we pose robust and tractable metric learning under pairwise constraints that are expressed as similarity judgements between data pairs. The major features of our approach include: 1) it maximizes the gap between the average squared distance among dissimilar pairs and the average squared distance among similar pairs; 2) it is capable of propagating similar constraints to all data pairs; and 3) it is easy to implement in contrast to the existing approaches using expensive optimization such as semidefinite programming. Our constrained metric learning approach has widespread applicability without being limited to particular backgrounds. Quantitative experiments are performed for classification and retrieval tasks, uncovering the effectiveness of the proposed approach.

APA, Harvard, Vancouver, ISO, and other styles

47

Kohl, Georg, Li-Wei Chen, and Nils Thuerey. "Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 8351–59. http://dx.doi.org/10.1609/aaai.v37i7.26007.

Full text

Abstract:

Simulations that produce three-dimensional data are ubiquitous in science, ranging from fluid flows to plasma physics. We propose a similarity model based on entropy, which allows for the creation of physically meaningful ground truth distances for the similarity assessment of scalar and vectorial data, produced from transport and motion-based simulations. Utilizing two data acquisition methods derived from this model, we create collections of fields from numerical PDE solvers and existing simulation data repositories. Furthermore, a multiscale CNN architecture that computes a volumetric similarity metric (VolSiM) is proposed. To the best of our knowledge this is the first learning method inherently designed to address the challenges arising for the similarity assessment of high-dimensional simulation data. Additionally, the tradeoff between a large batch size and an accurate correlation computation for correlation-based loss functions is investigated, and the metric's invariance with respect to rotation and scale operations is analyzed. Finally, the robustness and generalization of VolSiM is evaluated on a large range of test data, as well as a particularly challenging turbulence case study, that is close to potential real-world applications.

APA, Harvard, Vancouver, ISO, and other styles

48

Bazatbekov, Bek, Cemil Turan, Shirali Kadyrov, and Askhat Aitimov. "2D face recognition using PCA and triplet similarity embedding." Bulletin of Electrical Engineering and Informatics 12, no. 1 (February 1, 2023): 580–86. http://dx.doi.org/10.11591/eei.v12i1.4162.

Full text

Abstract:

The aim of this study is to propose a new robust face recognition algorithm by combining principal component analysis (PCA), Triplet Similarity Embedding based technique and Projection as a similarity metric at the different stages of the recognition processes. The main idea is to use PCA for feature extraction and dimensionality reduction, then train the triplet similarity embedding to accommodate changes in the facial poses, and finally use orthogonal projection as a similarity metric for classification. We use the open source ORL dataset to conduct the experiments to find the recognition rates of the proposed algorithm and compare them to the performance of one of the very well-known machine learning algorithms k-Nearest Neighbor classifier. Our experimental results show that the proposed model outperforms the kNN. Moreover, when the training set is smaller than the test set, the performance contribution of triplet similarity embedding during the learning phase becomes more visible compared to without it

APA, Harvard, Vancouver, ISO, and other styles

49

Sun, Zhiyu, Yusen He, Andrey Gritsenko, Amaury Lendasse, and Stephen Baek. "Embedded spectral descriptors: learning the point-wise correspondence metric via Siamese neural networks." Journal of Computational Design and Engineering 7, no. 1 (February 1, 2020): 18–29. http://dx.doi.org/10.1093/jcde/qwaa003.

Full text

Abstract:

Abstract A robust and informative local shape descriptor plays an important role in mesh registration. In this regard, spectral descriptors that are based on the spectrum of the Laplace–Beltrami operator have been a popular subject of research for the last decade due to their advantageous properties, such as isometry invariance. Despite such, however, spectral descriptors often fail to give a correct similarity measure for nonisometric cases where the metric distortion between the models is large. Hence, they are not reliable for correspondence matching problems when the models are not isometric. In this paper, it is proposed a method to improve the similarity metric of spectral descriptors for correspondence matching problems. We embed a spectral shape descriptor into a different metric space where the Euclidean distance between the elements directly indicates the geometric dissimilarity. We design and train a Siamese neural network to find such an embedding, where the embedded descriptors are promoted to rearrange based on the geometric similarity. We demonstrate our approach can significantly enhance the performance of the conventional spectral descriptors by the simple augmentation achieved via the Siamese neural network in comparison to other state-of-the-art methods.

APA, Harvard, Vancouver, ISO, and other styles

50

Lakman, I., R. Akhmetvaleev, D. Enikeev, R. Khaziakhmetov, and O. Chernenko. "Similarity Learning Algorithm Selection for Chronic Renal Failure Patients Treatment Strategy Optimization." INFORMACIONNYE TEHNOLOGII 26, no. 12 (December 15, 2020): 701–5. http://dx.doi.org/10.17587/it.26.701-705.

Full text

Abstract:

One of the main methods on which the personalized approach in medicine is based is finding a pair of patients who are similar in the properties of the disease. The objective of the study is to select the most effective similarity learning instrument amongst three options anaemia treatment and phosphorus-calcium balance recovery in dialysis patients, ranked according to the highest similarity to the particular patient. As soon as methods for comparing instruments will achieve the goal, the algorithm of weight tagging is used, modified by the authors by adding more weights values to important features — the cosine measure, the soft cosine measure, considering the similarity of drug alternative and their bioavailability. As a metric that evaluates the quality of algorithms, a combined metric is used that takes into account the quality of treatment classification as effective and the rank order of the greatest correspondence of therapy to a specific patient. As a result, using the opinions of nephrologists as experts, it was shown that the best measure of similarity is the soft cosine measure.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Similarity metric learning'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles