Duplex Generative Adversarial Network for Unsupervised Domain Adaptation

Hu, Lanqing; Kan, Meina; Shan, Shiguang; Chen, Xilin

doi:10.1109/cvpr.2018.00162

Cited by 160 publications

(107 citation statements)

References 18 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…GAN based domain adaptation methods [30,31,32,33] are also embraced in domain adaptation. Liu et al proposed coupled generative adversarial networks (CoGAN) [30] to learn a joint distribution of the source and target data where two classifiers are used for two domains and the classifiers are adapted so that the source classifier can classify the target samples correctly.…”

Section: Related Workmentioning

confidence: 99%

Correlation-aware adversarial domain adaptation and generalization

Rahman

Fookes

Baktashmotlagh

et al. 2020

Pattern Recognition

109

View full text Add to dashboard Cite

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different. The task of DG is more challenging than DA as the target data is totally unseen during the training phase in DG scenarios. The current state-of-the-art employs adversarial techniques, however, these are rarely considered for the DG problem. Furthermore, these approaches do not consider correlation alignment which has been proven highly beneficial for minimizing domain discrepancy. In this paper, we propose a correlation-aware adversarial DA and DG framework where the features of the source and target data are minimized using correlation alignment along with adversarial learning.Incorporating the correlation alignment module along with adversarial learning helps to achieve a more domain agnostic model due to the improved ability to reduce domain discrepancy with unlabeled target data more effectively. Experiments on benchmark datasets serve as evidence that our proposed method yields improved state-of-the-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Correlation-aware adversarial domain adaptation and generalization

Rahman

Fookes

Baktashmotlagh

et al. 2020

Pattern Recognition

109

View full text Add to dashboard Cite

show abstract

“…It is worth noting that our model not only reconstructs the opponent domain's images but also ensures that the reproduced image has the same class label with the original input image. Specifically, following previous work [Hu et al, 2018], our discriminators are designed such that it distinguishes the fake and the real, and at the same time predicts the label for real images. Thus, the output of a discriminator has N +1 distinct values, of which N values describe the image's labels and the last value defines whether the image is reconstructed or original.…”

Section: Semantic Discriminatorsmentioning

confidence: 99%

“…Difference from Duplex Both Duplex [Hu et al, 2018] and our framework adapt the generative adversarial networks to learn the common space to reduce domain disparity. However, Duplex uses only one generator to reconstruct cross-domain images, which requires it to add extra condition information to the common space, making it hard to align the two domains.…”

Section: Differences From Previous Workmentioning

confidence: 99%

“…We test our method on three public digits datasets: MNIST (M) [LeCun et al, 1998], SVHN (S) [Netzer et al, 2011], and USPS (U) [Denker et al, 1989]. Specifically, the three datasets have the same 10 categories but have various types.…”

Section: Datasetsmentioning

confidence: 99%

“…As for unsupervised domain adaption, one strategy is to train (under supervision) a classifier on the labeled source domain and then adapt it to a new domain. Some works [Hu et al, 2018] focus on how to assign high-confidence pseudo labels to the target domain and treat those predicted labels as the ground truth of the target domain to fine-tune the model. In [Zhang et al, 2018], the authors proposed a novel sample selection method aiming to select high-confidence labels.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Networks

Gao

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

With the recent explosive increase of digital data, image recognition and retrieval become a critical practical application. Hashing is an effective solution to this problem, due to its low storage requirement and high query speed. However, most of past works focus on hashing in a single (source) domain. Thus, the learned hash function may not adapt well in a new (target) domain that has a large distributional difference with the source domain. In this paper, we explore an end-to-end domain adaptive learning framework that simultaneously and precisely generates discriminative hash codes and classifies target domain images. Our method encodes two domains images into a semantic common space, followed by two independent generative adversarial networks arming at crosswise reconstructing two domains' images, reducing domain disparity and improving alignment in the shared space. We evaluate our framework on four public benchmark datasets, all of which show that our method is superior to the other state-of-the-art methods on the tasks of object recognition and image retrieval.

show abstract

Joint alignment network preserving structural information for multimode process fault diagnosis

Tan,

Xu,

Shi

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Production conditions are complex and varied for a number of reasons. Models for defect diagnosis may perform worse as a result of the distributional mismatch between test data and training data. In order to diagnose process faults, it is crucial to take into account the fact that data exhibits varied distribution characteristics under various conditions. In the case of multiple operating conditions, the cross‐domain problem caused by different data distributions can degrade the performance of deep learning‐based fault diagnosis models. To overcome this challenge, a joint alignment network preserving structural information (JANSI) method is proposed. To extract richer and fine‐grained domain‐invariant features, the structural information preservation is proposed, which combines domain labels, category labels, and data distribution structures. To increase intra‐class compactness and inter‐class separability, class centre alignment is proposed. The effectiveness of the method on the cross‐domain unsupervised fault diagnosis problem is verified through three case studies.

show abstract

Duplex Generative Adversarial Network for Unsupervised Domain Adaptation

Cited by 160 publications

References 18 publications

Correlation-aware adversarial domain adaptation and generalization

Correlation-aware adversarial domain adaptation and generalization

One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Networks

Joint alignment network preserving structural information for multimode process fault diagnosis

Contact Info

Product

Resources

About