# Aligned Contrastive Loss for Long-Tailed Recognition

Source: [Aligned Contrastive Loss for Long-Tailed Recognition](<https://www.sota2.com/research/paper/68fa78ff1e209131cea7b908>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:51:01.219Z

Authors: Jiali Ma, Jiequan Cui, Maeno Kazuki, Lakshmi Subramanian, Karlekar Jayashree, Sugiri Pranata, Hanwang Zhang

Published: 2025-06-01T16:19:30.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.01071>)

[PDF](<https://arxiv.org/pdf/2506.01071.pdf>)