Contrastive Adaptation Network for Unsupervised Domain Adaptation

Kang, Guoliang; Jiang, Lu; Yang, Yi; Hauptmann, Alexander G.

doi:10.1109/cvpr.2019.00503

Cited by 836 publications

(493 citation statements)

References 46 publications

Supporting

Mentioning

488

Contrasting

Unclassified

Order By: Relevance

“…In recent years, deep neural networks have been proved effectively in domain adaptation, and the existing methods based on deep neural network can be roughly divided into the following categories. The first category is based on discrepancy, i.e., the discrepancy between the features which are extracted from the source and target domains should be as small as possible, where the commonly used functions for measuring feature discrepancy are shown as follows: Maximum Mean Discrepancy (MMD) [3][4], Joint Maximum Mean Discrepancy (JMMD) [5], Weighted Maximum Mean Discrepancy (WMMD) [6], Wasserstein discrepancy [7], Sliced Wasserstein Discrepancy (SWD) [8], Orthogonal Discrepancy [9], Correlation Discrepancy [10][11][12], Source-Guided Discrepancy (SGD) [13], Contrastive Domain Discrepancy (CDD) [14] and pseudo-label differences [15][16]. Besides the marginal distributions, the output class distributions are also considered in domain adaptation [17].…”

Section: Related Workmentioning

confidence: 99%

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Jia

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes with similar features such as "bicycle" and "motorcycle". Therefore, a graph regularization based adversarial network model is proposed, whose innovations mainly include the following two aspects: First, a constraint function which is used to measure the difference between the features belonged to different classes is proposed, whose purpose is that not only the training accuracy is taken into account during supervised training, but also the difference between classes should be enlarged as much as possible; Then, a graph regularization constraint function is proposed, which makes all the classes have good local preserving properties after domain adaptation, and further reduces the possibility of all classes being misaligned. Experimental results on several cross-domain benchmark datasets show that our newly proposed approach outperforms state of the art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Jia

Sun

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…2) How to use multi-domain information and reduce the discrepancy between 2D images and 3D objects in a unified framework. Traditional domain adaptation works focus on single modality (e.g., 2D images) and obtain impressive performances [2,18,46,50]. Recently, there are some works paying attention to cross-domain retrieval, e.g., sketch-based 3D object retrieval [4,22,48] and image-based 3D object retrieval [24].…”

Section: Motivationmentioning

confidence: 99%

Domain-Specific Alignment Network for Multi-Domain Image-Based 3D Object Retrieval

Song

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

2D image-based 3D object retrieval is a very important task in computer vision and big data management. Conventional image-based 3D object retrieval usually assumes that the images are from one single domain. However, for real applications, 2D images may be from multiple domains (e.g., real image, sketch, and quick draw). It raises significant challenges for this task since these 2D images have a great domain gap with each other as well as a great modality gap with 3D objects. To address these issues, we propose an unsupervised Domain-Specific Alignment Network (DSAN) for multidomain image-based 3D object retrieval. The proposed method aims to reduce domain discrepancy by domain-specific alignment network with multi-level moment matching, including first-order moment and second-order moment. Based on the observation that for any given sample, different domain classifiers should output the same label, we design a domain-specific classifier alignment module. To our knowledge, the proposed method is the first unsupervised work to align multiple-domain 2D images with 3D objects in an end-to-end manner. The multi-domain dataset MDI3D is utilized to advocate the research on this task, and the extensive experimental results demonstrate the superiority of the proposed method. CCS CONCEPTS • Computing methodologies → Computer vision; Visual contentbased indexing and retrieval; • Information systems → Multimedia and multimodal retrieval.

show abstract

“…Transferrable Prototypical Networks (TPN) is presented for adaptation such that the prototypes for each class in the two domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar [33]. Contrastive Adaptation Network (CAN) is proposed to optimize a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy [34]. A dynamic Bayesian network (DBN)-based fault diagnosis methodology in the presence of TF and IF for electronic systems is proposed [35].…”

Section: Introductionmentioning

confidence: 99%

A New Transfer Learning Fault Diagnosis Method Using TSC and JGSA Under Variable Condition

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

It is very difficult to obtain the label data of rolling bearings under the complicated and variable working conditions, which results in low diagnosis accuracy. Transfer sparse coding(TSC) is a new feature representation method, which can effectively extract features from data matrix. Joint geometric and statistical alignment (JGSA) is a domain adaptation method, which can reduce the distribution shift and geometric shift between domains. In order to make full use of the feature extraction ability of the TSC and the transfer classification ability of the JGSA, a new transfer learing fault diagnosis(TSC-JGSA) method based on combining the characteristics of the TSC and JGSA is proposed to realize the fault diagnosis of rolling bearings under variable working conditions in this paper. In the TSC-JGSA, the fast Fourier transform technology is used to transform the time-domain signals into frequency-domain amplitudes. Then the TSC is used to effectively extract the deep features from the obtained frequency-domain amplitudes in order to construct a sparse feature matrix, which is input into the JGSA in order to realize the fault diagnosis of rolling bearings. Finally, the vibration data of rolling bearings under variable working conditions is used to prove the effectiveness of the TSC-JGSA. The experiment results show that the TSC-JGSA can effecrively solve the problem of lacking label data in actual engineering by using label data in the laboratory, and obtan higher diagnosis accuracy than other compared methods. It provides a new diagnosis idea for rotating machinery.

show abstract

Contrastive Adaptation Network for Unsupervised Domain Adaptation

Cited by 836 publications

References 46 publications

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Domain-Specific Alignment Network for Multi-Domain Image-Based 3D Object Retrieval

A New Transfer Learning Fault Diagnosis Method Using TSC and JGSA Under Variable Condition

Contact Info

Product

Resources

About