Bilateral Transformation of Biased Pseudo-Labels under Distribution Inconsistency
文献类型：期刊论文
| 作者 | Hou, Ruibing1; Chang, Hong1,2; Hu, Minyang1,2; Ma, Bingpeng1,2; Shan, Shiguang1,2; Chen, Xilin1,2 |
| 刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION
 |
| 出版日期 | 2026-01-29 |
| 卷号 | 134期号:3页码:34 |
| 关键词 | Self-training Semi-supervised learning Distribution inconsistency |
| ISSN号 | 0920-5691 |
| DOI | 10.1007/s11263-025-02701-2 |
| 英文摘要 | Typically self-training methods assign pseudo-labels by a source model and subsequently iteratively train the model with these pseudo-labeled samples. These approaches are widely employed to leverage vast reserves of unlabeled data, e.g., in semi-supervised learning (SSL) and unsupervised finetuning (UNF). However, our theoretical analysis reveals that the distribution inconsistency between source and unlabeled data could lead to a significant generation error bound for self-training methods. Motivated by this theoretical insight, we present a Bilateral Transformation Self-Training (BTST) learning approach to mitigate the distribution discrepancy and improve the generalization of self-training methods. Firstly, Representation Transformation Module (RTM) is designed to reduce representation distribution discrepancy by bidirectionally transforming high-level representations between source and unlabeled samples. Secondly, Logit Transformation Module (LTM) is designed to reduce class distribution discrepancy by aligning classifier's predictions with the unlabeled class distribution. Also, LTM incorporates a self-supervised regularization term to estimate unlabeled distribution, theoretically proven to effectively reduce estimation error bound. The two modules work complementary to reduce the generalization bound, ultimately achieving a more generalizable self-training model. Extensive experiments demonstrate that BTST can seamlessly integrate with self-training methods, improving their generalization across various SSL and UNF settings. |
| 资助项目 | National Natural Science Foundation of China[62376259] ; National Postdoctoral Program for Innovative Talents[BX20220310] ; National Natural Science Foundation of China (NSFC)[62306301] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001674370500005 |
| 出版者 | SPRINGER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42821]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Hou, Ruibing |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Hou, Ruibing,Chang, Hong,Hu, Minyang,et al. Bilateral Transformation of Biased Pseudo-Labels under Distribution Inconsistency[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2026,134(3):34. |
| APA | Hou, Ruibing,Chang, Hong,Hu, Minyang,Ma, Bingpeng,Shan, Shiguang,&Chen, Xilin.(2026).Bilateral Transformation of Biased Pseudo-Labels under Distribution Inconsistency.INTERNATIONAL JOURNAL OF COMPUTER VISION,134(3),34. |
| MLA | Hou, Ruibing,et al."Bilateral Transformation of Biased Pseudo-Labels under Distribution Inconsistency".INTERNATIONAL JOURNAL OF COMPUTER VISION 134.3(2026):34. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。