Catalyst: Out-of-Distribution Detection via Elastic Scaling

Abid Hassan, Tuan Ngo, Saad Shafiq, Nenad Medvidovic

Abstract: 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 introduce $\texttt{Catalyst}$, a post-hoc framework that exploits these under-explored signals. $\texttt{Catalyst}$, computes an input-dependent scaling factor ($\gamma$) on-the-fly from these raw statistics (e.g., mean, standard deviation, and maximum activation). This is then fused with the existing baseline score, multiplicatively modulating it -- an ``elastic scaling'' -- to push the ID and OOD distributions further apart. We demonstrate $\texttt{Catalyst}$, is a generalizable framework: it seamlessly integrates with logit-based methods (e.g., Energy, ReAct, SCALE) and also provides a significant boost to distance-based detectors like KNN. As a result, $\texttt{Catalyst}$, achieves substantial and consistent performance gains, reducing the average False Positive Rate by 32.87% on CIFAR-10 (ResNet-18), 27.94% on CIFAR-100 (ResNet-18), and 22.25% on ImageNet (ResNet-50). Our results highlight the untapped potential of pre-pooling statistics and demonstrate that $\texttt{Catalyst}$, is complementary to existing OOD detection approaches.