Region-adaptive Concept Aggregation for Few-shot Visual Recognition

doi:10.1007/s11633-022-1358-8

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Region-adaptive Concept Aggregation for Few-shot Visual Recognition
	Mengya Han 3,5,6
刊名	Machine Intelligence Research
	2023
卷号	20 期号:4 页码:554-568
关键词	Few-shot learning, metric-based meta learning, concept learning, region-adaptive, concept-aggregation
ISSN号	2731-538X
DOI	10.1007/s11633-022-1358-8
英文摘要	Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/52349]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore 2.School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China 3.JD Explore Academy, Beijing 101116, China 4.School of Computer Science, The University of Sydney, Sydney 2006, Australia 5.Hubei Luojia Laboratory, Wuhan 430072, China 6.School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, China
推荐引用方式 GB/T 7714	Mengya Han. Region-adaptive Concept Aggregation for Few-shot Visual Recognition[J]. Machine Intelligence Research,2023,20(4):554-568.
APA	Mengya Han.(2023).Region-adaptive Concept Aggregation for Few-shot Visual Recognition.Machine Intelligence Research,20(4),554-568.
MLA	Mengya Han."Region-adaptive Concept Aggregation for Few-shot Visual Recognition".Machine Intelligence Research 20.4(2023):554-568.