AI RESEARCH
DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation
arXiv CS.CV
•
ArXi:2601.22703v2 Announce Type: replace Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc detection methods operate on penultimate feature representations derived from global average pooling (GAP) -- a lossy operation that discards valuable distributional statistics from activation maps prior to global average pooling. We contend that these overlooked statistics, particularly channel-wise variance and dominant (maximum) activations, are highly discriminative for OOD detection. We