Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

2023-02-03 · Yumin Zhang, Yajun Gao, Hongliu Li, Ating Yin, Duzhen Zhang, Xiuyi Chen

Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.

📄 PDF Abstract BibTeX arXiv:2302.01708

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Unsupervised Domain Adaptation

An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

2019-12-18 · Jihan Yang, Ruijia Xu, Ruiyu Li, Xiaojuan Qi 외

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 dom…

Domain Adaptation Position Segmentation Semantic Segmentation+1

Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation

2021-06-08 · CVPR 2021 1 · Zhekai Du, Jingjing Li, Hongzu Su, Lei Zhu 외

Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. Recently, adversarial domain adaptation with two distinct classifiers (bi-cla…

Clustering Domain Adaptation Self-Supervised Learning Unsupervised Domain Adaptation

Collaborative and Adversarial Network for Unsupervised Domain Adaptation

2018-06-01 · CVPR 2018 6 · Weichen Zhang, Wanli Ouyang, Wen Li, Dong Xu

In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domain-adversarial training of neural networks. We use several d…

Domain Adaptation Unsupervised Domain Adaptation

Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing

2022-12-07 · Sarmad F. Ismael, Koray Kayabol, Erchan Aptoula

Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is cru…

Decoder Domain Adaptation Image-to-Image Translation Semantic Segmentation+1

Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks

2021-04-28 · Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan

Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversari…

Domain Adaptation Generative Adversarial Network Unsupervised Domain Adaptation