Log in

Relevant bibliographies by topics / Feature Adaptation / Journal articles

Journal articles on the topic 'Feature Adaptation'

To see the other types of publications on this topic, follow the link: Feature Adaptation.

Author: Grafiati

Published: 10 December 2022

Last updated: 28 January 2023

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

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Feature Adaptation.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

O'Brien, Michael J., and Thomas D. Holland. "The Role of Adaptation in Archaeological Explanation." American Antiquity 57, no. 1 (January 1992): 36–59. http://dx.doi.org/10.2307/2694834.

Full text

Abstract:

Adaptation, a venerable icon in archaeology, often is afforded the vacuous role of being an ex-post-facto argument used to "explain" the appearance and persistence of traits among prehistoric groups—a position that has seriously impeded development of a selectionist perspective in archaeology. Biological and philosophical definitions of adaptation—and by extension, definitions of adaptedness—vary considerably, but all are far removed from those usually employed in archaeology. The prevailing view in biology is that adaptations are features that were shaped by natural selection and that increase the adaptedness of an organism. Thus adaptations are separated from other features that may contribute to adaptedness but are products of other evolutionary processes. Analysis of adaptation comprises two stages: showing that a feature was under selection and how the feature functioned relative to the potential adaptedness of its bearers. The archaeological record contains a wealth of information pertinent to examining the adaptedness of prehistoric groups, but attempts to use it will prove successful only if a clear understanding exists of what adaptation is and is not.

APA, Harvard, Vancouver, ISO, and other styles

2

Cui, Pengcheng, Yongqian Zheng, Peimin Xu, Bin Li, Mingsheng Ma, and Guiyu Zhou. "The comparison of adjoint-based grid adaptation and feature-based grid adaptation method." Journal of Physics: Conference Series 2280, no. 1 (June 1, 2022): 012003. http://dx.doi.org/10.1088/1742-6596/2280/1/012003.

Full text

Abstract:

Abstract Grid adaption is a popular method to enhance the resolution of flow field and the precision of numerical simulation, which automatically optimizes the grid distribution instead of manual complicated work. There exist usually two grid adaptation methods, the feature based grid adaption and adjoint based grid adaption, the former focuses on shocks, vortexes and other features of flow field, and the latter focuses on lift, drag and other aerodynamic characteristics. The comparison of adjoint based grid adaption and feature based grid adaption method is investigated in this paper. Numerical simulations show that both feature adaption and adjoint adaption could improve the resolution of flow field and the precision of numerical simulation such as lift and drag. As for the flow features, the feature adaptation could capture the obvious shock waves and vortexes in the flow field, the adjoint adaptation, however, only captures the flow features that are contributory to the accuracy of aerodynamic characteristics. As for the aerodynamic characteristics, some shock waves and vortexes have little influences to the forces, so the feature adaptation is not efficient as adjoint adaptation, which could greatly improve the accuracy of aerodynamic characteristics.

APA, Harvard, Vancouver, ISO, and other styles

3

Qin, Ning, and Xueqiang Liu. "Flow feature aligned grid adaptation." International Journal for Numerical Methods in Engineering 67, no. 6 (2006): 787–814. http://dx.doi.org/10.1002/nme.1648.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Chen, Cheng, Qi Dou, Hao Chen, Jing Qin, and Pheng-Ann Heng. "Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 865–72. http://dx.doi.org/10.1609/aaai.v33i01.3301865.

Full text

Abstract:

This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in recent studies on deep learning, aiming to recover performance degradation when applying the neural networks to new testing domains. Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features towards the segmentation task. The feature encoder layers are shared by both perspectives to grasp their mutual benefits during the end-to-end learning procedure. Without using any annotation from the target domain, the learning of our unified model is guided by adversarial losses, with multiple discriminators employed from various aspects. We have extensively validated our method with a challenging application of crossmodality medical image segmentation of cardiac structures. Experimental results demonstrate that our SIFA model recovers the degraded performance from 17.2% to 73.0%, and outperforms the state-of-the-art methods by a significant margin.

APA, Harvard, Vancouver, ISO, and other styles

5

Li, Shuang, Chi Liu, Qiuxia Lin, Binhui Xie, Zhengming Ding, Gao Huang, and Jian Tang. "Domain Conditioned Adaptation Network." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 11386–93. http://dx.doi.org/10.1609/aaai.v34i07.6801.

Full text

Abstract:

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target. However, we argue that such strongly-shared convolutional layers might be harmful for domain-specific feature learning when source and target data distribution differs to a large extent. In this paper, we relax a shared-convnets assumption made by previous DA methods and propose a Domain Conditioned Adaptation Network (DCAN), which aims to excite distinct convolutional channels with a domain conditioned channel attention mechanism. As a result, the critical low-level domain-dependent knowledge could be explored appropriately. As far as we know, this is the first work to explore the domain-wise convolutional channel activation for deep DA networks. Moreover, to effectively align high-level feature distributions across two domains, we further deploy domain conditioned feature correction blocks after task-specific layers, which will explicitly correct the domain discrepancy. Extensive experiments on three cross-domain benchmarks demonstrate the proposed approach outperforms existing methods by a large margin, especially on very tough cross-domain learning tasks.

APA, Harvard, Vancouver, ISO, and other styles

6

Chen, Qingchao, and Yang Liu. "Structure-Aware Feature Fusion for Unsupervised Domain Adaptation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 10567–74. http://dx.doi.org/10.1609/aaai.v34i07.6629.

Full text

Abstract:

Unsupervised domain Adaptation (UDA) aims to learn and transfer generalized features from a labelled source domain to a target domain without any annotations. Existing methods only aligning high-level representation but without exploiting the complex multi-class structure and local spatial structure. This is problematic as 1) the model is prone to negative transfer when the features from different classes are misaligned; 2) missing the local spatial structure poses a major obstacle in performing the fine-grained feature alignment. In this paper, we integrate the valuable information conveyed in classifier prediction and local feature maps into global feature representation and then perform a single mini-max game to make it domain invariant. In this way, the domain-invariant feature not only describes the holistic representation of the original image but also preserves mode-structure and fine-grained spatial structural information. The feature integration is achieved by estimating and maximizing the mutual information (MI) among the global feature, local feature and classifier prediction simultaneously. As the MI is hard to measure directly in high-dimension spaces, we adopt a new objective function that implicitly maximizes the MI via an effective sampling strategy and a discriminator design. Our STructure-Aware Feature Fusion (STAFF) network achieves the state-of-the-art performances in various UDA datasets.

APA, Harvard, Vancouver, ISO, and other styles

7

Sun, Feng, Hanrui Wu, Zhihang Luo, Wenwen Gu, Yuguang Yan, and Qing Du. "Informative Feature Selection for Domain Adaptation." IEEE Access 7 (2019): 142551–63. http://dx.doi.org/10.1109/access.2019.2944226.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Li, Jingyao, Zhanshan Li, and Shuai Lü. "Feature concatenation for adversarial domain adaptation." Expert Systems with Applications 169 (May 2021): 114490. http://dx.doi.org/10.1016/j.eswa.2020.114490.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Wen, Jun, Risheng Liu, Nenggan Zheng, Qian Zheng, Zhefeng Gong, and Junsong Yuan. "Exploiting Local Feature Patterns for Unsupervised Domain Adaptation." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 5401–8. http://dx.doi.org/10.1609/aaai.v33i01.33015401.

Full text

Abstract:

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

APA, Harvard, Vancouver, ISO, and other styles

10

Stephens, John, and Sung-Ae Lee. "Transcultural Adaptation of Feature Films: South Korea’s My Sassy Girl and its Remakes." Adaptation 11, no. 1 (February 9, 2018): 75–95. http://dx.doi.org/10.1093/adaptation/apy001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Zhang, Zeqing, Zuodong Gao, Xiaofan Li, Cuihua Lee, and Weiwei Lin. "Information Separation Network for Domain Adaptation Learning." Electronics 11, no. 8 (April 15, 2022): 1254. http://dx.doi.org/10.3390/electronics11081254.

Full text

Abstract:

The Bai People have left behind a wealth of ancient texts that record their splendid civilization, unfortunately fewer and fewer people can read these texts in the present time. Therefore, it is of great practical value to design a model that can automatically recognize the Bai ancient (offset) texts. However, due to the expert knowledge involved in the annotation of ancient (offset) texts, and its limited scale, we consider that using handwritten Bai texts to help identify ancient (offset) Bai texts for handwritten Bai texts can be easily obtained and annotated. Essentially, this is a problem of domain adaptation, and some of the domain adaptation methods were transplanted to handle ancient (offset) Bai text recognition. Unfortunately, none of them succeeded in obtaining a high performance due to the fact that they do not solve the problem of how to separate the style and content information of an image. To address this, an information separation network (ISN) that can effectively separate content and style information and eventually classify with content features only, is proposed. Specifically, our network first divides the visual features into a style feature and a content feature by a separator, and ensures that the style feature contains only style and the content feature contains only content by cross-domain cross-reconstruction; thus, achieving the separation of style and content, and finally using only the content feature for classification. This greatly reduces the impact brought by cross-domain. The proposed method achieves leading results on five public datasets and a private one.

APA, Harvard, Vancouver, ISO, and other styles

12

Gardner, Andy. "The purpose of adaptation." Interface Focus 7, no. 5 (August 18, 2017): 20170005. http://dx.doi.org/10.1098/rsfs.2017.0005.

Full text

Abstract:

A central feature of Darwin's theory of natural selection is that it explains the purpose of biological adaptation. Here, I: emphasize the scientific importance of understanding what adaptations are for, in terms of facilitating the derivation of empirically testable predictions; discuss the population genetical basis for Darwin's theory of the purpose of adaptation, with reference to Fisher's ‘fundamental theorem of natural selection'; and show that a deeper understanding of the purpose of adaptation is achieved in the context of social evolution, with reference to inclusive fitness and superorganisms.

APA, Harvard, Vancouver, ISO, and other styles

13

Wang, Wei, Hao Wang, Zhi-Yong Ran, and Ran He. "Learning Robust Feature Transformation for Domain Adaptation." Pattern Recognition 114 (June 2021): 107870. http://dx.doi.org/10.1016/j.patcog.2021.107870.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Jung, Ho-Young Jung, Mansoo Park Park, Hoi-Rin Kim Kim, and Minsoo Hahn Hahn. "Speaker Adaptation Using ICA-Based Feature Transformation." ETRI Journal 24, no. 6 (December 1, 2002): 469–72. http://dx.doi.org/10.4218/etrij.02.0202.0003.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Akçay, Çağlar, and Eliot Hazeltine. "Domain-specific conflict adaptation without feature repetitions." Psychonomic Bulletin & Review 18, no. 3 (March 15, 2011): 505–11. http://dx.doi.org/10.3758/s13423-011-0084-y.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Wen, Jun, Junsong Yuan, Qian Zheng, Risheng Liu, Zhefeng Gong, and Nenggan Zheng. "Hierarchical domain adaptation with local feature patterns." Pattern Recognition 124 (April 2022): 108445. http://dx.doi.org/10.1016/j.patcog.2021.108445.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

JIANG, Chengming, Changyong JIAO, Huahua DONG, Wuheng ZUO, Lian XU, and Fengpei HU. "Cross-category Face Adaptation of Feature Association." Acta Psychologica Sinica 46, no. 8 (2014): 1072. http://dx.doi.org/10.3724/sp.j.1041.2014.01072.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Lee, Hyeopwoo, and Dongsuk Yook. "Feature adaptation for robust mobile speech recognition." IEEE Transactions on Consumer Electronics 58, no. 4 (November 2012): 1393–98. http://dx.doi.org/10.1109/tce.2012.6415011.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Prabuchandran, K. J., Shalabh Bhatnagar, and Vivek S. Borkar. "Actor-Critic Algorithms with Online Feature Adaptation." ACM Transactions on Modeling and Computer Simulation 26, no. 4 (May 2, 2016): 1–26. http://dx.doi.org/10.1145/2868723.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Tahmoresnezhad, Jafar, and Sattar Hashemi. "Visual domain adaptation via transfer feature learning." Knowledge and Information Systems 50, no. 2 (May 7, 2016): 585–605. http://dx.doi.org/10.1007/s10115-016-0944-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Wu, Lan, Chongyang Li, Qiliang Chen, and Binquan Li. "Deep adversarial domain adaptation network." International Journal of Advanced Robotic Systems 17, no. 5 (September 1, 2020): 172988142096464. http://dx.doi.org/10.1177/1729881420964648.

Full text

Abstract:

The advantage of adversarial domain adaptation is that it uses the idea of adversarial adaptation to confuse the feature distribution of two domains and solve the problem of domain transfer in transfer learning. However, although the discriminator completely confuses the two domains, adversarial domain adaptation still cannot guarantee the consistent feature distribution of the two domains, which may further deteriorate the recognition accuracy. Therefore, in this article, we propose a deep adversarial domain adaptation network, which optimises the feature distribution of the two confused domains by adding multi-kernel maximum mean discrepancy to the feature layer and designing a new loss function to ensure good recognition accuracy. In the last part, some simulation results based on the Office-31 and Underwater data sets show that the deep adversarial domain adaptation network can optimise the feature distribution and promote positive transfer, thus improving the classification accuracy.

APA, Harvard, Vancouver, ISO, and other styles

22

Chen, Minghao, Shuai Zhao, Haifeng Liu, and Deng Cai. "Adversarial-Learned Loss for Domain Adaptation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3521–28. http://dx.doi.org/10.1609/aaai.v34i04.5757.

Full text

Abstract:

Recently, remarkable progress has been made in learning transferable representation across domains. Previous works in domain adaptation are majorly based on two techniques: domain-adversarial learning and self-training. However, domain-adversarial learning only aligns feature distributions between domains but does not consider whether the target features are discriminative. On the other hand, self-training utilizes the model predictions to enhance the discrimination of target features, but it is unable to explicitly align domain distributions. In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA). We first analyze the pseudo-label method, a typical self-training method. Nevertheless, there is a gap between pseudo-labels and the ground truth, which can cause incorrect training. Thus we introduce the confusion matrix, which is learned through an adversarial manner in ALDA, to reduce the gap and align the feature distributions. Finally, a new loss function is auto-constructed from the learned confusion matrix, which serves as the loss for unlabeled target samples. Our ALDA outperforms state-of-the-art approaches in four standard domain adaptation datasets. Our code is available at https://github.com/ZJULearning/ALDA.

APA, Harvard, Vancouver, ISO, and other styles

23

Fu, Hongliang, Zhihao Zhuang, Yang Wang, Chen Huang, and Wenzhuo Duan. "Cross-Corpus Speech Emotion Recognition Based on Multi-Task Learning and Subdomain Adaptation." Entropy 25, no. 1 (January 7, 2023): 124. http://dx.doi.org/10.3390/e25010124.

Full text

Abstract:

To solve the problem of feature distribution discrepancy in cross-corpus speech emotion recognition tasks, this paper proposed an emotion recognition model based on multi-task learning and subdomain adaptation, which alleviates the impact on emotion recognition. Existing methods have shortcomings in speech feature representation and cross-corpus feature distribution alignment. The proposed model uses a deep denoising auto-encoder as a shared feature extraction network for multi-task learning, and the fully connected layer and softmax layer are added before each recognition task as task-specific layers. Subsequently, the subdomain adaptation algorithm of emotion and gender features is added to the shared network to obtain the shared emotion features and gender features of the source domain and target domain, respectively. Multi-task learning effectively enhances the representation ability of features, a subdomain adaptive algorithm promotes the migrating ability of features and effectively alleviates the impact of feature distribution differences in emotional features. The average results of six cross-corpus speech emotion recognition experiments show that, compared with other models, the weighted average recall rate is increased by 1.89%~10.07%, the experimental results verify the validity of the proposed model.

APA, Harvard, Vancouver, ISO, and other styles

24

Xiao, Ting, Cangning Fan, Peng Liu, and Hongwei Liu. "Simultaneously Improve Transferability and Discriminability for Adversarial Domain Adaptation." Entropy 24, no. 1 (December 27, 2021): 44. http://dx.doi.org/10.3390/e24010044.

Full text

Abstract:

Although adversarial domain adaptation enhances feature transferability, the feature discriminability will be degraded in the process of adversarial learning. Moreover, most domain adaptation methods only focus on distribution matching in the feature space; however, shifts in the joint distributions of input features and output labels linger in the network, and thus, the transferability is not fully exploited. In this paper, we propose a matrix rank embedding (MRE) method to enhance feature discriminability and transferability simultaneously. MRE restores a low-rank structure for data in the same class and enforces a maximum separation structure for data in different classes. In this manner, the variations within the subspace are reduced, and the separation between the subspaces is increased, resulting in improved discriminability. In addition to statistically aligning the class-conditional distribution in the feature space, MRE forces the data of the same class in different domains to exhibit an approximate low-rank structure, thereby aligning the class-conditional distribution in the label space, resulting in improved transferability. MRE is computationally efficient and can be used as a plug-and-play term for other adversarial domain adaptation networks. Comprehensive experiments demonstrate that MRE can advance state-of-the-art domain adaptation methods.

APA, Harvard, Vancouver, ISO, and other styles

25

Chen, Chao, Zhihong Chen, Boyuan Jiang, and Xinyu Jin. "Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 3296–303. http://dx.doi.org/10.1609/aaai.v33i01.33013296.

Full text

Abstract:

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift, target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate this issue, we propose to joint domain alignment and discriminative feature learning, which could benefit both domain alignment and final classification. Specifically, an instance-based discriminative feature learning method and a center-based discriminative feature learning method are proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Extensive experiments show that learning the discriminative features in the shared feature space can significantly boost the performance of deep domain adaptation methods.

APA, Harvard, Vancouver, ISO, and other styles

26

Lee, Seongmin, Hyunsik Jeon, and U. Kang. "Multi-EPL: Accurate multi-source domain adaptation." PLOS ONE 16, no. 8 (August 5, 2021): e0255754. http://dx.doi.org/10.1371/journal.pone.0255754.

Full text

Abstract:

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels. MSDA is a crucial problem applicable to many practical cases where labels for the target data are unavailable due to privacy issues. Existing MSDA frameworks are limited since they align data without considering labels of the features of each domain. They also do not fully utilize the target data without labels and rely on limited feature extraction with a single extractor. In this paper, we propose Multi-EPL, a novel method for MSDA. Multi-EPL exploits label-wise moment matching to align the conditional distributions of the features for the labels, uses pseudolabels for the unavailable target labels, and introduces an ensemble of multiple feature extractors for accurate domain adaptation. Extensive experiments show that Multi-EPL provides the state-of-the-art performance for MSDA tasks in both image domains and text domains, improving the accuracy by up to 13.20%.

APA, Harvard, Vancouver, ISO, and other styles

27

Gao, Yuan, Peipeng Chen, Yue Gao, Jinpeng Wang, YoungSun Pan, and Andy J. Ma. "Hierarchical feature disentangling network for universal domain adaptation." Pattern Recognition 127 (July 2022): 108616. http://dx.doi.org/10.1016/j.patcog.2022.108616.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Rakshit, Sayan, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee, Gemma Roig, and Subhasis Chaudhuri. "FRIDA — Generative feature replay for incremental domain adaptation." Computer Vision and Image Understanding 217 (March 2022): 103367. http://dx.doi.org/10.1016/j.cviu.2022.103367.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Zhao, Peng, Wenhua Zang, Bin Liu, Zhao Kang, Kun Bai, Kaizhu Huang, and Zenglin Xu. "Domain adaptation with feature and label adversarial networks." Neurocomputing 439 (June 2021): 294–301. http://dx.doi.org/10.1016/j.neucom.2021.01.062.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Zhang, Tianliang, Zhenjun Han, Huijuan Xu, Baochang Zhang, and Qixiang Ye. "CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection." IEEE Transactions on Intelligent Transportation Systems 21, no. 11 (November 2020): 4593–604. http://dx.doi.org/10.1109/tits.2019.2942045.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Wang, Meng, and Jiawei Fu. "A Triple Adversary Network Driven by Hybrid High-Order Attention for Domain Adaptation." Electronics 9, no. 12 (December 11, 2020): 2121. http://dx.doi.org/10.3390/electronics9122121.

Full text

Abstract:

How to bridge the knowledge gap between the annotated source domain and the unlabeled target domain is a basic challenge to domain adaptation. The existing approaches can relieve this gap by feature alignments across domains; however, aligning non-transferable features may lead to negative shift confusing the knowledge learning on target domains. In this paper, a triple adversary network is proposed on the basis of a high-order attention, hopefully to solve the problem. The proposed architecture focuses on the detailed feature alignment by a hybrid high-order attention using a fast iteration algorithm. In addition, an orthogonal loss of two complementary modules is applied to constrain the mutual exclusion of foreground and background features. Finally, a triple adversarial strategy is introduced to further improve the training convergence for the composed architectures. Numeric experiments on datasets of Digits, Office-31 and Office-home illuminate that the proposed network can effectively improve the state-of-art domain adaptations with superior transferring performance.

APA, Harvard, Vancouver, ISO, and other styles

32

Li, Xudong, Jianhua Zheng, Mingtao Li, Wenzhen Ma, and Yang Hu. "Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis." Sensors 21, no. 2 (January 10, 2021): 450. http://dx.doi.org/10.3390/s21020450.

Full text

Abstract:

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN.

APA, Harvard, Vancouver, ISO, and other styles

33

Li, Xudong, Jianhua Zheng, Mingtao Li, Wenzhen Ma, and Yang Hu. "Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis." Sensors 21, no. 2 (January 10, 2021): 450. http://dx.doi.org/10.3390/s21020450.

Full text

Abstract:

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN.

APA, Harvard, Vancouver, ISO, and other styles

34

Wang, Kai, Wei Zhao, Aidong Xu, Peng Zeng, and Shunkun Yang. "One-Dimensional Multi-Scale Domain Adaptive Network for Bearing-Fault Diagnosis under Varying Working Conditions." Sensors 20, no. 21 (October 23, 2020): 6039. http://dx.doi.org/10.3390/s20216039.

Full text

Abstract:

Data-driven bearing-fault diagnosis methods have become a research hotspot recently. These methods have to meet two premises: (1) the distributions of the data to be tested and the training data are the same; (2) there are a large number of high-quality labeled data. However, machines usually work under different working conditions in practice, which challenges these prerequisites due to the fact that the data distributions under different working conditions are different. In this paper, the one-dimensional Multi-Scale Domain Adaptive Network (1D-MSDAN) is proposed to address this issue. The 1D-MSDAN is a kind of deep transfer model, which uses both feature adaptation and classifier adaptation to guide the multi-scale convolutional neural network to perform bearing-fault diagnosis under varying working conditions. Feature adaptation is performed by both multi-scale feature adaptation and multi-level feature adaptation, which helps in finding domain-invariant features by minimizing the distribution discrepancy between different working conditions by using the Multi-kernel Maximum Mean Discrepancy (MK-MMD). Furthermore, classifier adaptation is performed by entropy minimization in the target domain to bridge the source classifier and target classifier to further eliminate domain discrepancy. The Case Western Reserve University (CWRU) bearing database is used to validate the proposed 1D-MSDAN. The experimental results show that the diagnostic accuracy for the 12 transfer tasks performed by 1D-MSDAN was superior to that of the mainstream transfer learning models for bearing-fault diagnosis under variable working conditions. In addition, the transfer learning performance of 1D-MSDAN for multi-target domain adaptation and real industrial scenarios was also verified.

APA, Harvard, Vancouver, ISO, and other styles

35

Zheng, Xiaorong, Zhaojian Gu, Caiming Liu, Jiahao Jiang, Zhiwei He, and Mingyu Gao. "Deep Transfer Network with Multi-Space Dynamic Distribution Adaptation for Bearing Fault Diagnosis." Entropy 24, no. 8 (August 15, 2022): 1122. http://dx.doi.org/10.3390/e24081122.

Full text

Abstract:

Domain adaptation-based bearing fault diagnosis methods have recently received high attention. However, the extracted features in these methods fail to adequately represent fault information due to the versatility of the work scenario. Moreover, most existing adaptive methods attempt to align the feature space of domains by calculating the sum of marginal distribution distance and conditional distribution distance, without considering variable cross-domain diagnostic scenarios that provide significant cues for fault diagnosis. To address the above problems, we propose a deep convolutional multi-space dynamic distribution adaptation (DCMSDA) model, which consists of two core components: two feature extraction modules and a dynamic distribution adaptation module. Technically, a multi-space structure is proposed in the feature extraction module to fully extract fault features of the marginal distribution and conditional distribution. In addition, the dynamic distribution adaptation module utilizes different metrics to capture distribution discrepancies, as well as an adaptive coefficient to dynamically measure the alignment proportion in complex cross-domain scenarios. This study compares our method with other advanced methods, in detail. The experimental results show that the proposed method has excellent diagnosis performance and generalization performance. Furthermore, the results further demonstrate the effectiveness of each transfer module proposed in our model.

APA, Harvard, Vancouver, ISO, and other styles

36

Tao, Hui, Jun He, Quanjie Cao, and Lei Zhang. "Adversarial Hard Attention Adaptation." Information 11, no. 4 (April 18, 2020): 224. http://dx.doi.org/10.3390/info11040224.

Full text

Abstract:

Domain adaptation is critical to transfer the invaluable source domain knowledge to the target domain. In this paper, for a particular visual attention model, saying hard attention, we consider to adapt the learned hard attention to the unlabeled target domain. To tackle this kind of hard attention adaptation, a novel adversarial reward strategy is proposed to train the policy of the target domain agent. In this adversarial training framework, the target domain agent competes with the discriminator which takes the attention features generated from the both domain agents as input and tries its best to distinguish them, and thus the target domain policy is learned to align the local attention feature to its source domain counterpart. We evaluated our model on the benchmarks of the cross-domain tasks, such as the centered digits datasets and the enlarged non-centered digits datasets. The experimental results show that our model outperforms the ADDA and other existing methods.

APA, Harvard, Vancouver, ISO, and other styles

37

Yang, Jihan, Ruijia Xu, Ruiyu Li, Xiaojuan Qi, Xiaoyong Shen, Guanbin Li, and Liang Lin. "An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 12613–20. http://dx.doi.org/10.1609/aaai.v34i07.6952.

Full text

Abstract:

We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally. However, this strategy fails in adapting the representations of the tail classes or small objects for semantic segmentation since the alignment objective is dominated by head categories or large objects. In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations. Specifically, we firstly perturb the intermediate feature maps with several attack objectives (i.e., discriminator and classifier) on each individual position for both domains, and then the classifier is trained to be invariant to the perturbations. By perturbing each position individually, our model treats each location evenly regardless of the category or object size and thus circumvents the aforementioned issue. Moreover, the domain gap in feature space is reduced by extrapolating source and target perturbed features towards each other with attack on the domain discriminator. Our approach achieves the state-of-the-art performance on two challenging domain adaptation tasks for semantic segmentation: GTA5 → Cityscapes and SYNTHIA → Cityscapes.

APA, Harvard, Vancouver, ISO, and other styles

38

Kumagai, Atsutoshi, and Tomoharu Iwata. "Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 4106–13. http://dx.doi.org/10.1609/aaai.v33i01.33014106.

Full text

Abstract:

We propose a simple yet effective method for unsupervised domain adaptation. When training and test distributions are different, standard supervised learning methods perform poorly. Semi-supervised domain adaptation methods have been developed for the case where labeled data in the target domain are available. However, the target data are often unlabeled in practice. Therefore, unsupervised domain adaptation, which does not require labels for target data, is receiving a lot of attention. The proposed method minimizes the discrepancy between the source and target distributions of input features by transforming the feature space of the source domain. Since such unilateral transformations transfer knowledge in the source domain to the target one without reducing dimensionality, the proposed method can effectively perform domain adaptation without losing information to be transfered. With the proposed method, it is assumed that the transformed features and the original features differ by a small residual to preserve the relationship between features and labels. This transformation is learned by aligning the higher-order moments of the source and target feature distributions based on the maximum mean discrepancy, which enables to compare two distributions without density estimation. Once the transformation is found, we learn supervised models by using the transformed source data and their labels. We use two real-world datasets to demonstrate experimentally that the proposed method achieves better classification performance than existing methods for unsupervised domain adaptation.

APA, Harvard, Vancouver, ISO, and other styles

39

Rashedi, Esmat, Hossein Nezamabadi-pour, and Saeid Saryazdi. "A simultaneous feature adaptation and feature selection method for content-based image retrieval systems." Knowledge-Based Systems 39 (February 2013): 85–94. http://dx.doi.org/10.1016/j.knosys.2012.10.011.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Niu, Chang, Junyuan Shang, Zhiheng Zhou, Junchu Huang, Tianlei Wang, and Xiangwei Li. "Common‐specific feature learning for multi‐source domain adaptation." IET Image Processing 14, no. 16 (December 2020): 4049–58. http://dx.doi.org/10.1049/iet-ipr.2019.1712.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Zhang, Kuangen, Jiahong Chen, Jing Wang, Yuquan Leng, Clarence W. de Silva, and Chenglong Fu. "Gaussian-guided feature alignment for unsupervised cross-subject adaptation." Pattern Recognition 122 (February 2022): 108332. http://dx.doi.org/10.1016/j.patcog.2021.108332.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Ouareth, Selma, Boulehouache Soufiane, and Mazouzi Smaine. "Self-Adaptation Through Reinforcement Learning Using a Feature Model." International Journal of Organizational and Collective Intelligence 12, no. 4 (October 1, 2022): 1–20. http://dx.doi.org/10.4018/ijoci.312226.

Full text

Abstract:

Typically, self-adaptation is achieved by implementing the MAPE-K Control Loop. The researchers agree that multiple control loops should be assigned if the system is complex and large-scale. The hierarchical control has proven to be a good compromise to achieve SAS goals, as there is always some degree of decentralization but it also retains a degree of centralization. The decentralized entities must be coordinated to ensure the consistency of adaptation processes. The high cost of data transfer between coordinating entities may be an obstacle to achieving system scalability. To resolve this problem, coordination should only define between entities that require communication between them. However, most of the current SAS relies on static MAPE-K. In this article, authors present a new method that allows changing the structure and behavior of loops. Authors base on exploration strategies for online reinforcement learning, using the feature model to define the adaptation space.

APA, Harvard, Vancouver, ISO, and other styles

43

Nguyen, Hien V., Huy Tho Ho, Vishal M. Patel, and Rama Chellappa. "DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning." IEEE Transactions on Image Processing 24, no. 12 (December 2015): 5479–91. http://dx.doi.org/10.1109/tip.2015.2479405.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Stern, R., and M. Lasry. "Dynamic speaker adaptation for feature-based isolated word recognition." IEEE Transactions on Acoustics, Speech, and Signal Processing 35, no. 6 (June 1987): 751–63. http://dx.doi.org/10.1109/tassp.1987.1165203.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Fang, Wen-Chieh, and Yi-Ting Chiang. "A discriminative feature mapping approach to heterogeneous domain adaptation." Pattern Recognition Letters 106 (April 2018): 13–19. http://dx.doi.org/10.1016/j.patrec.2018.02.011.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Tabebordbar, Alireza, Amin Beheshti, Boualem Benatallah, and Moshe Chai Barukh. "Feature-Based and Adaptive Rule Adaptation in Dynamic Environments." Data Science and Engineering 5, no. 3 (June 25, 2020): 207–23. http://dx.doi.org/10.1007/s41019-020-00130-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Kallinderis, Yannis, Eleni M. Lymperopoulou, and Panagiotis Antonellis. "Flow feature detection for grid adaptation and flow visualization." Journal of Computational Physics 341 (July 2017): 182–207. http://dx.doi.org/10.1016/j.jcp.2017.04.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Hoffman, Judy, Erik Rodner, Jeff Donahue, Brian Kulis, and Kate Saenko. "Asymmetric and Category Invariant Feature Transformations for Domain Adaptation." International Journal of Computer Vision 109, no. 1-2 (April 13, 2014): 28–41. http://dx.doi.org/10.1007/s11263-014-0719-3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Ma, Chenhui, Dexuan Sha, and Xiaodong Mu. "Unsupervised Adversarial Domain Adaptation with Error-Correcting Boundaries and Feature Adaption Metric for Remote-Sensing Scene Classification." Remote Sensing 13, no. 7 (March 26, 2021): 1270. http://dx.doi.org/10.3390/rs13071270.

Full text

Abstract:

Unsupervised domain adaptation (UDA) based on adversarial learning for remote-sensing scene classification has become a research hotspot because of the need to alleviating the lack of annotated training data. Existing methods train classifiers according to their ability to distinguish features from source or target domains. However, they suffer from the following two limitations: (1) the classifier is trained on source samples and forms a source-domain-specific boundary, which ignores features from the target domain and (2) semantically meaningful features are merely built from the adversary of a generator and a discriminator, which ignore selecting the domain invariant features. These issues limit the distribution matching performance of source and target domains, since each domain has its distinctive characteristic. To resolve these issues, we propose a framework with error-correcting boundaries and feature adaptation metric. Specifically, we design an error-correcting boundaries mechanism to build target-domain-specific classifier boundaries via multi-classifiers and error-correcting discrepancy loss, which significantly distinguish target samples and reduce their distinguished uncertainty. Then, we employ a feature adaptation metric structure to enhance the adaptation of ambiguous features via shallow layers of the backbone convolutional neural network and alignment loss, which automatically learns domain invariant features. The experimental results on four public datasets outperform other UDA methods of remote-sensing scene classification.

APA, Harvard, Vancouver, ISO, and other styles

50

Li, Ping, Zhiwei Ni, Xuhui Zhu, Juan Song, and Wenying Wu. "Optimal Transport with Dimensionality Reduction for Domain Adaptation." Symmetry 12, no. 12 (December 3, 2020): 1994. http://dx.doi.org/10.3390/sym12121994.

Full text

Abstract:

Domain adaptation manages to learn a robust classifier for target domain, using the source domain, but they often follow different distributions. To bridge distribution shift between the two domains, most of previous works aim to align their feature distributions through feature transformation, of which optimal transport for domain adaptation has attract researchers’ interest, as it can exploit the local information of the two domains in the process of mapping the source instances to the target ones by minimizing Wasserstein distance between their feature distributions. However, it may weaken the feature discriminability of source domain, thus degrade domain adaptation performance. To address this problem, this paper proposes a two-stage feature-based adaptation approach, referred to as optimal transport with dimensionality reduction (OTDR). In the first stage, we apply the dimensionality reduction with intradomain variant maximization but source intraclass compactness minimization, to separate data samples as much as possible and enhance the feature discriminability of the source domain. In the second stage, we leverage optimal transport-based technique to preserve the local information of the two domains. Notably, the desirable properties in the first stage can mitigate the degradation of feature discriminability of the source domain in the second stage. Extensive experiments on several cross-domain image datasets validate that OTDR is superior to its competitors in classification accuracy.

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!