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
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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Ma CC(马成丞)]的文章
[Dong WM(董未名)]的文章
[Xu CS(徐常胜)]的文章
百度学术
百度学术中相似的文章
[Ma CC(马成丞)]的文章
[Dong WM(董未名)]的文章
[Xu CS(徐常胜)]的文章
必应学术
必应学术中相似的文章
[Ma CC(马成丞)]的文章
[Dong WM(董未名)]的文章
[Xu CS(徐常胜)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: MIR_SSFSL_final_version.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。