An Iterative Co-Training Transductive Framework for Zero Shot Learning | |
Liu, Bo1,2; Hu, Lihua3; Dong, Qiulei1,2,4; Hu, Zhanyi1,2 | |
刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
![]() |
2021 | |
卷号 | 30页码:6943-6956 |
关键词 | Visualization Semantics Training Feature extraction Testing Detectors Predictive models Zero-shot learning transductive learning co-training |
ISSN号 | 1057-7149 |
DOI | 10.1109/TIP.2021.3100552 |
通讯作者 | Dong, Qiulei(qldong@nlpr.ia.ac.cn) |
英文摘要 | In zero-shot learning (ZSL) community, it is generally recognized that transductive learning performs better than inductive one as the unseen-class samples are also used in its training stage. How to generate pseudo labels for unseen-class samples and how to use such usually noisy pseudo labels are two critical issues in transductive learning. In this work, we introduce an iterative co-training framework which contains two different base ZSL models and an exchanging module. At each iteration, the two different ZSL models are co-trained to separately predict pseudo labels for the unseen-class samples, and the exchanging module exchanges the predicted pseudo labels, then the exchanged pseudo-labeled samples are added into the training sets for the next iteration. By such, our framework can gradually boost the ZSL performance by fully exploiting the potential complementarity of the two models' classification capabilities. In addition, our co-training framework is also applied to the generalized ZSL (GZSL), in which a semantic-guided OOD detector is proposed to pick out the most likely unseen-class samples before class-level classification to alleviate the bias problem in GZSL. Extensive experiments on three benchmarks show that our proposed methods could significantly outperform about 31 state-of-the-art ones. |
资助项目 | National Natural Science Foundation of China (NSFC)[61991423] ; National Natural Science Foundation of China (NSFC)[U1805264] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32050100] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000682121800005 |
资助机构 | National Natural Science Foundation of China (NSFC) ; Strategic Priority Research Program of the Chinese Academy of Sciences |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/45622] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
通讯作者 | Dong, Qiulei |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100049, Peoples R China 3.Taiyuan Univ Sci & Technol, Sch Comp Sci & Technol, Taiyuan 030024, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Bo,Hu, Lihua,Dong, Qiulei,et al. An Iterative Co-Training Transductive Framework for Zero Shot Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:6943-6956. |
APA | Liu, Bo,Hu, Lihua,Dong, Qiulei,&Hu, Zhanyi.(2021).An Iterative Co-Training Transductive Framework for Zero Shot Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,6943-6956. |
MLA | Liu, Bo,et al."An Iterative Co-Training Transductive Framework for Zero Shot Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):6943-6956. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论