Feature Fusion from Head to Tail for Long-Tailed Visual Recognition

TL;DR

This paper introduces head-to-tail fusion (H2T), a simple yet effective method that enhances tail class features by combining them with head class information, improving long-tailed visual recognition performance.

Contribution

The paper proposes a novel feature augmentation technique, H2T, that improves tail class recognition by grafting semantic information from head classes, and demonstrates its effectiveness across benchmarks.

Findings

H2T improves tail class accuracy in long-tailed recognition.

H2T is a plug-and-play module compatible with existing methods.

Extensive experiments validate the effectiveness of H2T.

Abstract

The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.