Instance-Level Embedding Adaptation for Few-Shot Learning | |
Hao, Fusheng1,2,3; Cheng, Jun3,4; Wang, Lei3,4; Cao, Jianzhong1![]() | |
刊名 | IEEE ACCESS
![]() |
2019 | |
卷号 | 7页码:100501-100511 |
关键词 | Attention adaptation module deep neural networks few-shot learning |
ISSN号 | 2169-3536 |
DOI | 10.1109/ACCESS.2019.2906665 |
产权排序 | 1 |
英文摘要 | Few-shot learning aims to recognize novel categories from just a fewlabeled instances. Existing metric learning-based approaches perform classifications by nearest neighbor search in the embedding space. The embedding function is a deep neural network and usually shared by all novel categories. However, these brute approaches lack a fast adaptation mechanism like meta-learning when dealing with novel categories. To tackle this, we present a novel instance-level embedding adaptation mechanism, aiming at rapidly adapting embedding deep features to improve their generalization ability in recognizing novel categories. To this end, we design an Attention Adaptation Module to pull a query instance and its corresponding class center as close as possible. Note that, each query instance is pulled closer to its corresponding class center before performing nearest neighbor classifications. This instance-level reduction of intra-class distance increases the probability of correct classifications, and thus improves the generalization ability to embed deep features and promoting the performance. The extensive experiments are conducted on two benchmark datasets: miniImageNet and CUB. Our approach yields very promising results on both datasets. In addition, in a realistic cross-domain evaluation setting, our method also achieves the-state-of-the-art performance. |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000481688500001 |
内容类型 | 期刊论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/31816] ![]() |
专题 | 西安光学精密机械研究所_动态光学成像研究室 |
通讯作者 | Cheng, Jun |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Virtual Real & Human Interact Te, Shenzhen 518055, Peoples R China 4.Chinese Univ Hong Kong, Hong Kong, Peoples R China |
推荐引用方式 GB/T 7714 | Hao, Fusheng,Cheng, Jun,Wang, Lei,et al. Instance-Level Embedding Adaptation for Few-Shot Learning[J]. IEEE ACCESS,2019,7:100501-100511. |
APA | Hao, Fusheng,Cheng, Jun,Wang, Lei,&Cao, Jianzhong.(2019).Instance-Level Embedding Adaptation for Few-Shot Learning.IEEE ACCESS,7,100501-100511. |
MLA | Hao, Fusheng,et al."Instance-Level Embedding Adaptation for Few-Shot Learning".IEEE ACCESS 7(2019):100501-100511. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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