Introspective GAN: Learning to grow a GAN for incremental generation and classification

doi:10.1016/j.patcog.2024.110383

	Introspective GAN: Learning to grow a GAN for incremental generation and classification
	He, Chen 1; Wang, Ruiping 1; Shan, Shiguang 1; Chen, Xilin 1
	2024-07-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	151 页码:12
摘要	Lifelong learning, the ability to continually learn new concepts throughout our life, is a hallmark of human intelligence. Generally, humans learn a new concept by knowing what it looks like and what makes it different from the others , which are correlated. Those two ways can be characterized by generation and classification in machine learning respectively. In this paper, we carefully design a dynamically growing GAN called Introspective GAN (IntroGAN) that can perform incremental generation and classification simultaneously with the guidance of prototypes, inspired by their roles of efficient information organization in human visual learning and excellent performance in other fields like zero-shot/few-shot/incremental learning. Specifically, we incorporate prototype-based classification which is robust to feature change in incremental learning and GAN as a generative memory to alleviate forgetting into a unified end -to -end framework. A comprehensive benchmark on the joint incremental generation and classification task is proposed and our method demonstrates promising results. Additionally, we conduct comprehensive analyses over the properties of IntroGAN and verify that generation and classification can be mutually beneficial in incremental scenarios, which is an inspiring area to be further exploited. The code is available at https://github.com/TonyPod/ IntroGAN.
关键词	Incremental learning Catastrophic forgetting Generative Adversarial Networks
DOI	10.1016/j.patcog.2024.110383
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2021ZD0111901] ; Natural Science Foundation of China[U21B2025] ; Natural Science Foundation of China[U19B2036]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001221726400001
出版者	ELSEVIER SCI LTD
引用统计	被引频次：2[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/2XEOYT63/38987
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ruiping
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, CAS, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	He, Chen,Wang, Ruiping,Shan, Shiguang,et al. Introspective GAN: Learning to grow a GAN for incremental generation and classification[J]. PATTERN RECOGNITION,2024,151:12.
APA	He, Chen,Wang, Ruiping,Shan, Shiguang,&Chen, Xilin.(2024).Introspective GAN: Learning to grow a GAN for incremental generation and classification.PATTERN RECOGNITION,151,12.
MLA	He, Chen,et al."Introspective GAN: Learning to grow a GAN for incremental generation and classification".PATTERN RECOGNITION 151(2024):12.