AI RESEARCH
Catalyst: Out-of-Distribution Detection via Elastic Scaling
arXiv CS.CV
•
ArXi:2602.02409v2 Announce Type: replace Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive OOD scores from the output logits or penultimate feature vector obtained via global average pooling (GAP). We contend that this exclusive reliance on the logit or feature vector discards a rich, complementary signal: the raw channel-wise statistics of the pre-pooling feature map lost in GAP. In this paper, we.