Yazhou Yao

Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

2024 · arXiv (Cornell University)

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and discard …

Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric

2024 · arXiv (Cornell University)

Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to maximize inter-class discrepancy and minimize …