The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Outlier-Aware Contrastive Learning
- Published
- Record updated
Summary
This study proposes an outlier-aware contrastive learning method for high-fidelity embeddings. It addresses sampling bias, where similar samples from different classes create false negatives, by using OOD detection to mask them in a debiased contrastive loss. Because prior knowledge of OOD samples is usually unavailable, the authors generate synthesized OOD samples near the boundary between in-distribution (ID) and OOD data, learning an OOD detector from these samples and ID data. The source reports experiments illustrating the merit of the approach.