A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition

TL;DR

This paper introduces a dual-branch model with contrastive loss to improve long-tailed recognition, enhancing tail class adaptation and decision boundary clarity in imbalanced datasets.

Contribution

The proposed DB-LTR model combines an imbalanced learning branch with a contrastive learning branch, effectively addressing data imbalance and improving tail class recognition.

Findings

Outperforms existing methods on CIFAR100-LT, ImageNet-LT, and Places-LT datasets.

Effectively learns discriminative features for tail classes.

Enhances decision boundary clarity in long-tailed data.

Abstract

Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the decision boundaries are ambiguous. Therefore, in this paper, we propose a simple yet effective model, named Dual-Branch Long-Tailed Recognition (DB-LTR), which includes an imbalanced learning branch and a Contrastive Learning Branch (CoLB). The imbalanced learning branch, which consists of a shared backbone and a linear classifier, leverages common imbalanced learning approaches to tackle the data imbalance issue. In CoLB, we learn a prototype for each tail class, and calculate an inter-branch contrastive loss, an intra-branch contrastive loss and a metric loss. CoLB can improve the capability of the model in adapting to tail classes and assist the imbalanced learning branch to learn a well-represented feature space and discriminative decision boundary. Extensive experiments on three long-tailed benchmark datasets, i.e., CIFAR100-LT, ImageNet-LT and Places-LT, show that our DB-LTR is competitive and superior to the comparative methods.