Compound Batch Normalization for Long-Tailed Image Classification

Lechao Cheng, Chaowei Fang, Dingwen Zhang, Guanbin Li, Gang Huang

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

Significant progress has been made in learning image classification neural networks under long-Tail data distribution using robust training algorithms such as data re-sampling, re-weighting, and margin adjustment. Those methods, however, ignore the impact of data imbalance on feature normalization. The dominance of majority classes (head classes) in estimating statistics and affine parameters causes internal covariate shifts within less-frequent categories to be overlooked. To alleviate this challenge, we propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. In addition, a moving average-based expectation maximization (EM) algorithm is employed to estimate the statistical parameters of multiple Gaussian distributions. However, the EM algorithm is sensitive to initialization and can easily become stuck in local minima where the multiple Gaussian components continue to focus on majority classes. To tackle this issue, we developed a dual-path learning framework that employs class-Aware split feature normalization to diversify the estimated Gaussian distributions, allowing the Gaussian components to fit with training samples of less-frequent classes more comprehensively. Extensive experiments on commonly used datasets demonstrated that the proposed method outperforms existing methods on long-Tailed image classification.

源语言英语
主期刊名MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia
出版商Association for Computing Machinery, Inc
1925-1934
页数10
ISBN(电子版)9781450392037
DOI
出版状态已出版 - 10 10月 2022
活动30th ACM International Conference on Multimedia, MM 2022 - Lisboa, 葡萄牙
期限: 10 10月 202214 10月 2022

出版系列

姓名MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia

会议

会议30th ACM International Conference on Multimedia, MM 2022
国家/地区葡萄牙
Lisboa
时期10/10/2214/10/22

指纹

探究 'Compound Batch Normalization for Long-Tailed Image Classification' 的科研主题。它们共同构成独一无二的指纹。

引用此