Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

TLDR

The authors aim to develop a lightweight training paradigm that enhances feature robustness and reduces classifier bias toward head classes in long‑tail visual recognition. They introduce GLMC, a one‑stage method that applies a global MixUp and local CutMix to generate paired augmented batches, uses cosine similarity to enforce mixture consistency, and reweights head‑tail soft labels based on empirical class frequencies, balancing the standard and reweighted losses with an epoch‑accumulated coefficient. GLMC achieves state‑of‑the‑art accuracy on CIFAR10‑LT, CIFAR100‑LT, and ImageNet‑LT, and further boosts backbone generalization on balanced ImageNet and CIFAR datasets. Code is publicly available at https://github.com/ynu-yangpeng/GLMC.

Abstract

In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead. We propose an efficient one-stage training strategy for long-tailed visual recognition called Global and Local Mixture Consistency cumulative learning (GLMC). Our core ideas are twofold: (1) a global and local mixture consistency loss improves the robustness of the feature extractor. Specifically, we generate two augmented batches by the global MixUp and local CutMix from the same batch data, respectively, and then use cosine similarity to minimize the difference. (2) A cumulative head-tail soft label reweighted loss mitigates the head class bias problem. We use empirical class frequencies to reweight the mixed label of the head-tail class for long-tailed data and then balance the conventional loss and the rebalanced loss with a coefficient accumulated by epochs. Our approach achieves state-of-the-art accuracy on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT datasets. Additional experiments on balanced ImageNet and CIFAR demonstrate that GLMC can significantly improve the gen-eralization of backbones. Code is made publicly available at https://github.com/ynu-yangpeng/GLMC.