MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer
文献类型:期刊论文
作者 | Wang, Wenjian4,5,6; Duan, Lijuan4,5,6; Wang, Yuxi3; Fan, Junsong; Zhang, Zhaoxiang1,2,3 |
刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
出版日期 | 2023-12-01 |
卷号 | 45期号:12页码:15018-15035 |
ISSN号 | 0162-8828 |
关键词 | Memory few-shot learning semantic segmentation cross-domain |
DOI | 10.1109/TPAMI.2023.3306352 |
通讯作者 | Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn) |
英文摘要 | Few-shot learning aims to recognize novel categories solely relying on a few labeled samples, with existing few-shot methods primarily focusing on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured, and the actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we investigate an interesting and challenging cross-domain few-shot learning task, where the training and testing tasks employ different domains. Specifically, we propose aMeta-Memory scheme to bridge the domain gap between source and target domains, leveraging style-memory and content-memory components. The former stores intra-domain style information from source domain instances and provides a richer feature distribution. The latter stores semantic information through exploration of knowledge of different categories. Under the contrastive learning strategy, our model effectively alleviates the cross-domain problem in few-shot learning. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on cross-domain few-shot semantic segmentation tasks on the COCO-20(i), PASCAL-5(i), FSS-1000, and SUIM datasets and positively affects few-shot classification tasks on Meta-Dataset. |
WOS关键词 | NETWORKS |
资助项目 | National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; National Natural Science Foundation of China[62006231] ; National Natural Science Foundation of China[62176009] ; Major Project for New Generation of AI[2018AAA0100400] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE COMPUTER SOC |
WOS记录号 | WOS:001130146400060 |
资助机构 | National Natural Science Foundation of China ; Major Project for New Generation of AI |
源URL | [http://ir.ia.ac.cn/handle/173211/55515] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Zhang, Zhaoxiang |
作者单位 | 1.Univ Chinese Acad Sci UCAS, Beijing 101408, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100045, Peoples R China 3.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong 999077, Peoples R China 4.Natl Engn Lab Key Technol Informat Secur Level Pr, Beijing 100124, Peoples R China 5.Beijing Key Lab Trusted Comp, Beijing 100124, Peoples R China 6.Beijing Univ Technol, Fac Informat Technol, Beijing 100021, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Wenjian,Duan, Lijuan,Wang, Yuxi,et al. MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15018-15035. |
APA | Wang, Wenjian,Duan, Lijuan,Wang, Yuxi,Fan, Junsong,&Zhang, Zhaoxiang.(2023).MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15018-15035. |
MLA | Wang, Wenjian,et al."MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15018-15035. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。