Constructing Balance from Imbalance for Long-tailed Image Recognition

TL;DR

This paper introduces a novel approach to long-tailed image recognition by balancing label space before classifier training, improving performance across various models and benchmarks.

Contribution

It proposes a label space balancing paradigm that adjusts head and tail class distributions prior to classifier learning, enhancing long-tailed recognition.

Findings

Boosts performance of state-of-the-art models on benchmarks

Provides a feature evaluation method for long-tailed data

Easily integrable with existing classification models

Abstract

Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural networks. Previous methods tackle with data imbalance from the viewpoints of data distribution, feature space, and model design, etc. In this work, instead of directly learning a recognition model, we suggest confronting the bottleneck of head-to-tail bias before classifier learning, from the previously omitted perspective of balancing label space. To alleviate the head-to-tail bias, we propose a concise paradigm by progressively adjusting label space and dividing the head classes and tail classes, dynamically constructing balance from imbalance to facilitate the classification. With flexible data filtering and label space mapping, we can easily embed our approach to most classification models, especially the decoupled training methods. Besides, we find the separability of head-tail classes varies among different features with different inductive biases. Hence, our proposed model also provides a feature evaluation method and paves the way for long-tailed feature learning. Extensive experiments show that our method can boost the performance of state-of-the-arts of different types on widely-used benchmarks. Code is available at https://github.com/silicx/DLSA.