Knowledge Commons of Institute of Automation,CAS
Learning by Seeing More Classes | |
Fei Zhu; Xu-Yao Zhang; Rui-Qi Wang; Cheng-Lin Liu | |
发表期刊 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
2022-10-28 | |
卷号 | 45期号:6页码:7477-7493 |
文章类型 | Regular paper |
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. |
关键词 | Class augmentation generalization confidence estimation open-environment learning |
DOI | 10.1109/TPAMI.2022.3225117 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000982475600058 |
七大方向——子方向分类 | 模式识别基础 |
国重实验室规划方向分类 | 人工智能基础前沿理论 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52409 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.University of Chinese Academy of Sciences, Beijing, 100049, 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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Learning_by_Seeing_M(2561KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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