Knowledge Commons of Institute of Automation,CAS
TENET: Beyond Pseudo-Labeling for Semi-supervised Few-shot Learning | |
Ma CC(马成丞)1,2; Dong WM(董未名)1; Xu CS(徐常胜)1 | |
发表期刊 | Machine Intelligence Research |
2023-09 | |
页码 | 0 |
摘要 | Few-shot learning attempts to identify novel categories by exploiting limited labeled training data, while the performances of existing methods still have much room for improvement. Thanks to a very low cost, many recent methods resort to additional unlabeled training data to boost performance, known as semi-supervised few-shot learning (SSFSL). The general idea of SSFSL methods is to first generate pseudo labels for all unlabeled data and then augment the labeled training set with selected pseudo-labeled data. However, almost all previous SSFSL methods only take supervision signal from pseudo-labeling, ignoring that the distribution of training data can also be utilized as an effective unsupervised regularization. In this paper, we propose a simple yet effective SSFSL method named TENET, which takes low-rank feature reconstruction as the unsupervised objective function and pseudo labels as the supervised constraint. We provide several theoretical insights on why TENET can mitigate overfitting on low-quality training data, and why it can enhance the robustness against inaccurate pseudo labels. Extensive experiments on four popular datasets validate the effectiveness of TENET. |
关键词 | Semi-supervised few-shot learning few-shot learning pseudo-labeling linear regression low-rank reconstruction |
语种 | 英语 |
七大方向——子方向分类 | 机器学习 |
国重实验室规划方向分类 | 小样本高噪声数据学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/54588 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Dong WM(董未名) |
作者单位 | 1.Chinese Academy of Sciences, Institution of Automation, National Lab Pattern Recognition, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China |
推荐引用方式 GB/T 7714 | Ma CC,Dong WM,Xu CS. TENET: Beyond Pseudo-Labeling for Semi-supervised Few-shot Learning[J]. Machine Intelligence Research,2023:0. |
APA | Ma CC,Dong WM,&Xu CS.(2023).TENET: Beyond Pseudo-Labeling for Semi-supervised Few-shot Learning.Machine Intelligence Research,0. |
MLA | Ma CC,et al."TENET: Beyond Pseudo-Labeling for Semi-supervised Few-shot Learning".Machine Intelligence Research (2023):0. |
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 | ||
MIR_SSFSL_final_vers(741KB) | 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