文献类型：期刊文献

英文题名：Learning to Capture the Query Distribution for Few-Shot Learning

作者：Chi, Ziqiu[1,2];Wang, Zhe[1,2];Yang, Mengping[1,2];Li, Dongdong[1,2];Du, Wenli[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：32

期号：7

起止页码：4163

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20214511141168);WOS:【SCI-EXPANDED(收录号:WOS:000819817700008)】；

基金：This work was supported in part by the Shanghai Science and Technology Program "Distributed and Generative Few-Shot Algorithm and Theory Research" under Grant 20511100600, in part by the Shanghai Science and Technology Program "Federated Based Cross-Domain and Cross-Task Incremental Learning" under Grant 21511100800, in part by the Natural Science Foundation of China under Grant 62076094, in part by the Natural Science Foundations of China under Grant 61806078, and in part by the National Science Foundation of China for Distinguished Young Scholars under Grant 61725301. This article was recommended by Associate Editor J. Sreevalsan-Nair.

语种：英文

外文关键词：Few-shot learning; image classification; deep learning

摘要：In the Few-Shot Learning (FSL), much of the related efforts only rely on the few available labeled samples (support set) building approach. However, the challenge is that the support set is easy-to-be-biased, so that they cannot be competent prototypes and are hard to represent the class distribution, leading to performance bottlenecks. In this paper, we propose to solve this obstacle by capturing the distribution of the unlabeled samples (query set). We propose two sampling methods: DeepSearch (DS) and WideSearch (WS). Both approaches are simple to implement and have no trainable parameters. They search the query samples near to the support set in different manners. Afterward, the statistic information is calculated, and we generate the latent samples according to it. The generated latent set is promising. First, it brings the query set distribution information to the classifier, which significantly improves the performance of the cross-entropy-based classifier. Second, it helps the support set become the better prototypes, which boosts the performance of the prototype-based classifier. Third, we find few latent samples are enough to boost the performance. Abundant experiments prove the proposed method achieves state-of-the-art performance on the few-shot tasks. Finally, rich ablation studies explain the compelling details of our approach.