Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
Li, Zhuo, Zhao, He, Li, Zhen, Liu, Tongliang, Guo, Dandan, Wan, Xiang
–arXiv.org Artificial Intelligence
Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples. Despite their effectiveness, they may be limited in handling the joint issue effectively in a unified way. In this work, we develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching, which can be solved with optimal transport (OT). By setting a manually-specific probability measure and using a learned transport plan to pseudo-label the training samples, the proposed method can reduce the side-effects of noisy and long-tailed data simultaneously. Then we introduce a simple yet effective filter criteria by combining the observed labels and pseudo labels to obtain a more balanced and less noisy subset for a robust model training. Extensive experiments demonstrate that our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
arXiv.org Artificial Intelligence
Apr-10-2024
- Country:
- Europe > Switzerland > Zürich > Zürich (0.14)
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Neural Networks (0.47)
- Statistical Learning (0.46)
- Representation & Reasoning (0.92)
- Vision (0.94)
- Machine Learning
- Data Science (1.00)
- Artificial Intelligence
- Information Technology