Learning by Seeing More Classes
文献类型:期刊论文
作者 | Fei Zhu; Xu-Yao Zhang; Rui-Qi Wang; Cheng-Lin Liu |
刊名 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
出版日期 | 2022-10-28 |
卷号 | 45期号:6页码:7477-7493 |
关键词 | Class augmentation generalization confidence estimation open-environment learning |
DOI | 10.1109/TPAMI.2022.3225117 |
文献子类 | Regular paper |
英文摘要 | Traditional pattern recognition models usually assume a fixed and identical number of classes during both training and inference stages. In this paper, we study an interesting but ignored question: can increasing the number of classes during training improve the generalization and reliability performance? For a k-class problem, instead of training with only these k classes, we propose to learn with k + m classes, where the additional m classes can be either real classes from other datasets or synthesized from known classes. Specifically, we propose two strategies for constructing new classes from known classes. By making the model see more classes during training, we can obtain several advantages. First, the added m classes serve as a regularization which is helpful to improve the generalization accuracy on the original k classes. Second, this will alleviate the overconfident phenomenon and produce more reliable confidence estimation for different tasks like misclassification detection, confidence calibration, and out-of-distribution detection. Lastly, the additional classes can also improve the learned feature representation, which is beneficial for new classes generalization in few-shot learning and class-incremental learning. Compared with the widely proved concept of data augmentation (dataAug), our method is driven from another dimension of augmentation based on additional classes (classAug). Comprehensive experiments demonstrated the superiority of our classAug under various open-environment metrics on benchmark datasets. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/52409] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing, 100049, China 2.NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Fei Zhu,Xu-Yao Zhang,Rui-Qi Wang,et al. Learning by Seeing More Classes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(6):7477-7493. |
APA | Fei Zhu,Xu-Yao Zhang,Rui-Qi Wang,&Cheng-Lin Liu.(2022).Learning by Seeing More Classes.IEEE Transactions on Pattern Analysis and Machine Intelligence,45(6),7477-7493. |
MLA | Fei Zhu,et al."Learning by Seeing More Classes".IEEE Transactions on Pattern Analysis and Machine Intelligence 45.6(2022):7477-7493. |
入库方式: OAI收割
来源:自动化研究所
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。