Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning

doi:10.1109/TNNLS.2020.3011526

	Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning
	Lai, Nan 1,2; Kan, Meina 1,2; Han, Chunrui 1,2; Song, Xingguang 3; Shan, Shiguang 1,2,4
	2021-08-01
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
卷号	32 期号:8 页码:3458-3470
摘要	Few-shot learning aims to learn a well-performing model from a few labeled examples. Recently, quite a few works propose to learn a predictor to directly generate model parameter weights with episodic training strategy of meta-learning and achieve fairly promising performance. However, the predictor in these works is task-agnostic, which means that the predictor cannot adjust to novel tasks in the testing phase. In this article, we propose a novel meta-learning method to learn how to learn task-adaptive classifier-predictor to generate classifier weights for few-shot classification. Specifically, a meta classifier-predictor module, (MPM) is introduced to learn how to adaptively update a task-agnostic classifier-predictor to a task-specialized one on a novel task with a newly proposed center-uniqueness loss function. Compared with previous works, our task-adaptive classifier-predictor can better capture characteristics of each category in a novel task and thus generate a more accurate and effective classifier. Our method is evaluated on two commonly used benchmarks for few-shot classification, i.e., miniImageNet and tieredImageNet. Ablation study verifies the necessity of learning task-adaptive classifier-predictor and the effectiveness of our newly proposed center-uniqueness loss. Moreover, our method achieves the state-of-the-art performance on both benchmarks, thus demonstrating its superiority.
关键词	Task analysis Adaptation models Training Predictive models Feature extraction Generators Computational modeling Few-shot learning meta-learning predict classifier weights task-adaptive predictor
DOI	10.1109/TNNLS.2020.3011526
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0700800] ; Natural Science Foundation of China[61772496] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2017145]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000681169500019
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：73[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/17408
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Kan, Meina
作者单位	1.Chinese Acad Sci, Inst Comp Technol ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Huawei Technol Co Ltd, Shenzhen 518129, Peoples R China 4.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Lai, Nan,Kan, Meina,Han, Chunrui,et al. Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(8):3458-3470.
APA	Lai, Nan,Kan, Meina,Han, Chunrui,Song, Xingguang,&Shan, Shiguang.(2021).Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(8),3458-3470.
MLA	Lai, Nan,et al."Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.8(2021):3458-3470.