文献类型：期刊文献

英文题名：Complementary features based prototype self-updating for few-shot learning

作者：Xu, Xinlei[1];Wang, Zhe[1,2];Chi, Ziqiu[1,2];Yang, Hai[1,2];Du, Wenli[1,2]

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：2023

卷号：214

外文期刊名：EXPERT SYSTEMS WITH APPLICATIONS

收录：;EI(收录号：20224413043337);WOS:【SCI-EXPANDED(收录号:WOS:000883786000013)】；

基金：This work is supported by Shanghai Science and Technology Program Federated based cross-domain and cross-task incremental learning'' under Grant No. 21511100800, Shanghai Science and Technology Program Distributed and generative few-shot algorithm and theory research'' under Grant No. 20511100600, Natural Science Foundation of China under Grant No. 62076094, Chinese Defense Program of Scienceand Technology under Grant No. 2021-JCJQ-JJ-0041, China AerospaceScience and Technology Corporation Industry-University-Research Co-operation Foundation of the Eighth Research Institute under Grant No.SAST2021-007

语种：英文

外文关键词：Few-shot learning; Prototype learning; Complementary features

摘要：The goal of few-shot learning is to use limited labeled samples to complete independent classification tasks. The feature extractor of few-shot learning needs to have a stronger feature expression ability to generalizein unseen novel classes. To further enhance the expressive ability, in this paper, we propose an inherited feature extraction method, named Base and Meta Feature Extraction (BMFE). Base feature represents the task-irrelevant classification information of each sample. Meta feature obtained by the proposed Triplet Meta-train Mechanism (TMM) inherits the classification information and also contains the task-related meta information of each sample. We concatenate both the base and meta features to complementarily express the rich information of each sample. Besides, instead of relying on limited support samples to obtain the prototype, we propose a novel unsupervised prototype correction module, named Prototype Self-updating (PSU). All unlabeled query samples in a few-shot test task participate in the iterative updating of each prototype in the task without training. Extensive experiments prove that our overall method can obtain richer features by BMFE and more accurate prototypes by PSU. Our overall method outperforms state-of-the-art methods on miniImageNet and tired ImageNet datasets, and especially under the 1-shot case we obtains 78.45% and 81.21% classification accuracy respectively