Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation

TL;DR

This paper introduces GLAG, a novel method combining a gradual balanced loss and adaptive feature generation to improve long-tailed classification, achieving state-of-the-art results on multiple datasets.

Contribution

The paper presents a new approach that enhances long-tailed classification by jointly learning balanced features and augmenting tail classes at the feature level.

Findings

Achieves state-of-the-art results on CIFAR100-LT, ImageNetLT, and iNaturalist.

Demonstrates effectiveness of combining balanced loss with feature augmentation.

Improves performance of long-tailed visual recognition models.

Abstract

The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG first learns a balanced and robust feature model with Gradual Balanced Loss, then fixes the feature model and augments the under-represented tail classes on the feature level with the knowledge from well-represented head classes. And the generated samples are mixed up with real training samples during training epochs. Gradual Balanced Loss is a general loss and it can combine with different decoupled training methods to improve the original performance. State-of-the-art results have been achieved on long-tail datasets such as CIFAR100-LT, ImageNetLT, and iNaturalist, which demonstrates the effectiveness of GLAG for long-tailed visual recognition.