BCE3S: Binary Cross-Entropy Based Tripartite Synergistic Learning for Long-tailed Recognition

TL;DR

This paper introduces BCE3S, a novel tripartite learning framework based on binary cross-entropy, to improve feature compactness, inter-class separability, and classifier balance in long-tailed recognition tasks, achieving state-of-the-art results.

Contribution

The paper proposes BCE3S, a new method that decouples feature and classifier learning, incorporates contrastive and uniform learning, and outperforms existing methods on long-tailed datasets.

Findings

Achieves higher feature compactness and separability.

Balances classifier vector separability.

Outperforms state-of-the-art on multiple datasets.

Abstract

For long-tailed recognition (LTR) tasks, high intra-class compactness and inter-class separability in both head and tail classes, as well as balanced separability among all the classifier vectors, are preferred. The existing LTR methods based on cross-entropy (CE) loss not only struggle to learn features with desirable properties but also couple imbalanced classifier vectors in the denominator of its Softmax, amplifying the imbalance effects in LTR. In this paper, for the LTR, we propose a binary cross-entropy (BCE)-based tripartite synergistic learning, termed BCE3S, which consists of three components: (1) BCE-based joint learning optimizes both the classifier and sample features, which achieves better compactness and separability among features than the CE-based joint learning, by decoupling the metrics between feature and the imbalanced classifier vectors in multiple Sigmoid; (2) BCE-based contrastive learning further improves the intra-class compactness of features; (3) BCE-based uniform learning balances the separability among classifier vectors and interactively enhances the feature properties by combining with the joint learning. The extensive experiments show that the LTR model trained by BCE3S not only achieves higher compactness and separability among sample features, but also balances the classifier's separability, achieving SOTA performance on various long-tailed datasets such as CIFAR10-LT, CIFAR100-LT, ImageNet-LT, and iNaturalist2018.