Weight-guided class complementing for long-tailed image recognition. (June 2023)

• Record Type: Journal Article
• Authors: Zhao, Xinqiao; Xiao, Jimin; Yu, Siyue; Li, Hui; Zhang, Bingfeng
• Is Part Of: Pattern recognition. Volume 138(2023)
• Publication Date: 2023-06
• Subjects: Image recognition -- Long-tailed distribution -- Gradient shift -- Weight-guided method; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109374
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a weight-guided class complementing framework to mitigate the gradient shift issue caused by unsampled classes in long-tailed scenario, including a slot-based class complementing strategy and a weight-guided feature mining loss. We further introduce a weight refining scheme at the end of training process, which can remove the bias term in our weight-guided class complementing framework caused by long-tailed distribution. Our plug-and-play weight-guided class complementing framework can be easily implemented to different existing approaches, achieving significant improvement on various benchmarks with new state-of-the-art performances. Abstract: Real-world data are often long-tailed distributed and have plenty classes. This characteristic leads to a significant performance drop for various models. One reason behind that is the gradient shift caused by unsampled classes in each training iteration. In this paper, we propose a W eight-G uided C lass C omplementing framework to address this issue. Specifically, this framework first complements the unsampled classes in each training iteration by using a dynamic updated data slot. Then, considering the over-fitting issue caused by class complementing, we utilize the classifier weights as learned knowledge and encourage the model to discover more class specific characteristics. Finally, we design a weight refining scheme to deal with the long-tailed bias existing in classifier weights. Experimental results show that our framework can be implemented upon different existing approaches effectively, achieving consistent improvements on various benchmarks with new state-of-the-art performances. Codes will be released.