Frequency-Aware Self-Supervised Long-Tailed Learning
This addresses the challenge of data imbalance in real-world scenarios where labels are unavailable, offering a self-supervised solution for long-tailed learning.
The paper tackles the problem of learning from unlabeled data with long-tailed distributions by proposing Frequency-Aware Self-Supervised Learning (FASSL), which learns frequency-aware prototypes and exploits relationships to produce discriminative features, with experiments on image datasets verifying its effectiveness.
Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been proposed to tackle such data imbalance, the requirement of label supervision would limit their applicability to real-world scenarios in which label annotation might not be available. Without the access to class labels nor the associated class frequencies, we propose Frequency-Aware Self-Supervised Learning (FASSL) in this paper. Targeting at learning from unlabeled data with inherent long-tailed distributions, the goal of FASSL is to produce discriminative feature representations for downstream classification tasks. In FASSL, we first learn frequency-aware prototypes, reflecting the associated long-tailed distribution. Particularly focusing on rare-class samples, the relationships between image data and the derived prototypes are further exploited with the introduced self-supervised learning scheme. Experiments on long-tailed image datasets quantitatively and qualitatively verify the effectiveness of our learning scheme.