Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

被引:130
作者
Chen, Lin [1 ]
Chen, Huaian [1 ]
Wei, Zhixiang [1 ]
Jin, Xin [1 ]
Tan, Xiao [1 ]
Jin, Yi [1 ]
Chen, Enhong [1 ]
机构
[1] Univ Sci & Technol China, Hefei, Peoples R China
来源
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2022年
基金
中国国家自然科学基金;
关键词
D O I
10.1109/CVPR52688.2022.00704
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to play the min-max game with a feature extractor. However, most of these methods failed to effectively leverage the predicted discriminative information, and thus cause mode collapse for generator. In this work, we address this problem from a different perspective and design a simple yet effective adversarial paradigm in the form of a discriminator-free adversarial learning network (DALN), wherein the category classifier is reused as a discriminator, which achieves explicit domain alignment and category distinguishment through a unified objective, enabling the DALN to leverage the predicted discriminative information for sufficient feature alignment. Basically, we introduce a Nuclear-norm Wasserstein discrepancy (NWD) that has definite guidance meaning for performing discrimination. Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy. Without bells and whistles, DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets. Moreover, as a plug-and-play technique, NWD can be directly used as a generic regularizer to benefit existing UDA algorithms. Code is available at https://github.com/xiaoachen98/DALN.
引用
收藏
页码:7171 / 7180
页数:10
相关论文
共 51 条
[1]  
[Anonymous], 2011, P 28 INT C MACH LEAR
[2]  
[Anonymous], 2004, NIPS
[3]  
Arjovsky M, 2017, PR MACH LEARN RES, V70
[4]  
Ben-David S., 2006, NIPS
[5]  
Caputo B, 2014, INT C CROSS LANG EV, P192, DOI DOI 10.1007/978-3-319-11382-118
[6]   End-to-End Object Detection with Transformers [J].
Carion, Nicolas ;
Massa, Francisco ;
Synnaeve, Gabriel ;
Usunier, Nicolas ;
Kirillov, Alexander ;
Zagoruyko, Sergey .
COMPUTER VISION - ECCV 2020, PT I, 2020, 12346 :213-229
[7]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[8]  
Chen XY, 2019, PR MACH LEARN RES, V97
[9]  
Cui SH, 2021, Arxiv, DOI arXiv:2107.06154
[10]   Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations [J].
Cui, Shuhao ;
Wang, Shuhui ;
Zhuo, Junbao ;
Li, Liang ;
Huang, Qingming ;
Tian, Qi .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :3940-3949