Score: 1

Aligned Contrastive Loss for Long-Tailed Recognition

Published: June 1, 2025 | arXiv ID: 2506.01071v1

By: Jiali Ma , Jiequan Cui , Maeno Kazuki and more

Potential Business Impact:

Teaches computers to recognize rare things better.

Business Areas:
Image Recognition Data and Analytics, Software

In this paper, we propose an Aligned Contrastive Learning (ACL) algorithm to address the long-tailed recognition problem. Our findings indicate that while multi-view training boosts the performance, contrastive learning does not consistently enhance model generalization as the number of views increases. Through theoretical gradient analysis of supervised contrastive learning (SCL), we identify gradient conflicts, and imbalanced attraction and repulsion gradients between positive and negative pairs as the underlying issues. Our ACL algorithm is designed to eliminate these problems and demonstrates strong performance across multiple benchmarks. We validate the effectiveness of ACL through experiments on long-tailed CIFAR, ImageNet, Places, and iNaturalist datasets. Results show that ACL achieves new state-of-the-art performance.

Country of Origin
πŸ‡ΈπŸ‡¬ Singapore

Page Count
10 pages

Category
Computer Science:
CV and Pattern Recognition