Long-Tailed Recognition via Information-Preservable Two-Stage Learning
This work addresses the challenge of long-tailed recognition for improving model fairness and accuracy in real-world applications, representing a novel method for a known bottleneck.
The paper tackles the problem of class imbalance in deep classification models, which leads to poor performance on tail classes, by proposing a two-stage learning approach that achieves state-of-the-art results on various long-tailed benchmark datasets.
The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-biased tendency while preserving valuable information within datasets. Specifically, the first stage proposes a new representation learning technique from the information theory perspective. This approach is theoretically equivalent to minimizing intra-class distance, yielding an effective and well-separated feature space. The second stage develops a novel sampling strategy that selects mathematically informative instances, able to rectify majority-biased decision boundaries without compromising a model's overall performance. As a result, our approach achieves the state-of-the-art performance across various long-tailed benchmark datasets, validated via extensive experiments. Our code is available at https://github.com/fudong03/BNS_IPDPP.