Stable Attribute Group Editing for Reliable Few-Shot Image Generation

doi:10.1109/TCSVT.2025.3578670

CSpace

	Stable Attribute Group Editing for Reliable Few-Shot Image Generation
	Ding, Guanqi 1,2; Han, Xinzhe 5; Wang, Shuhui 2,3; Jin, Xin 4; Huang, Qingming 1,2,3
	2025-12-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	35 期号:12 页码:12719-12733
摘要	Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and few-shot classification. To achieve this goal, the generated images should guarantee category retention for classification beyond the visual quality and diversity. In our preliminary work, we present an "editing-based" framework, Attribute Group Editing (AGE), for reliable few-shot image generation, which largely improves the performance compared with existing methods that require re-training a GAN with limited data. Nevertheless, AGE's performance on downstream classification is not as satisfactory as expected. Furthermore, existing generative models suffer from similar issues. This paper focuses on addressing the issue of universal class inconsistency in all generative models. It not only improves AGE to enhance its ability to preserve class information but also conducts a comprehensive analysis of the causes of this problem in generative models from multiple perspectives, proposing potential directions for resolution. We first propose Stable Attribute Group Editing (SAGE) for more stable class-relevant image generation. SAGE corrects the inaccurate assumptions in AGE and leverages the distribution information from seen categories to accurately estimate the data distribution of unseen categories, thereby eliminating the class inconsistency issue in the generated data. We apply SAGE to both GANs and diffusion models to verify its flexibility and further achieve promising generation performance. Going one step further, we find that even though the generated images look photo-realistic and require no category-relevant editing, they are usually of limited help for downstream classification. We systematically discuss this issue from both the generation and classification perspectives, and propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components. Extensive experiments provide valuable insights into extending image generation to wider downstream applications. Codes are available at https://github.com/UniBester/SAGE
关键词	Image synthesis Training Diffusion models Dictionaries Generators Data models Codes Visualization Reliability Analytical models Few-shot image generation generative adversarial network image editing
DOI	10.1109/TCSVT.2025.3578670
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001631874000018
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42984
专题	中国科学院计算技术研究所
通讯作者	Wang, Shuhui
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518066, Peoples R China 4.Huawei Cloud EI Innovat Lab, Beijing 100085, Peoples R China 5.China Acad Aerosp Syst & Innovat CASI, China Aerosp Sci & Technol Corperat CASC, Beijing 100088, Peoples R China
推荐引用方式 GB/T 7714	Ding, Guanqi,Han, Xinzhe,Wang, Shuhui,et al. Stable Attribute Group Editing for Reliable Few-Shot Image Generation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2025,35(12):12719-12733.
APA	Ding, Guanqi,Han, Xinzhe,Wang, Shuhui,Jin, Xin,&Huang, Qingming.(2025).Stable Attribute Group Editing for Reliable Few-Shot Image Generation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,35(12),12719-12733.
MLA	Ding, Guanqi,et al."Stable Attribute Group Editing for Reliable Few-Shot Image Generation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 35.12(2025):12719-12733.