Search Results for author:
Found 2 papers, 1 papers with code
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns.
Detecting Out-of-distribution Examples via Class-conditional Impressions Reappearing
Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
