Papers › Weight-guided class complementing for long-tailed image recognition

Weight-guided class complementing for long-tailed image recognition

3 Feb 2023Pattern Recognition 2023 2archive 2025-07-28

Xinqiao Zhao, Jimin Xiao, Siyue Yu, Hui Li, Bingfeng Zhang

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 Weight-Guided Class Complementing 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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Long-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-10-LT (ρ=100) NCL* + WGCC (ensemble) Error Rate 15.4 #12 of 28 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) NCL* + WGCC (ensemble) Error Rate 44.9 #12 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) LDAM-DRW + WGCC Error Rate 56.4 #55 of 66 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections