LSF: Layer Selection and Fusion for Post-Hoc Out-of-Distribution Detection

Distance-based out-of-distribution detection typically relies on the penultimate representation, whose optimization for ID class discrimination may suppress lower-level variation useful for detecting distribution shifts. We introduce LSF (Layer Selection and Fusion for OOD detection), a post-hoc framework that exploits complementary information across network layers. LSF selects an intermediate layer with the largest decrease in entropy density between consecutive layers and concatenates it with the penultimate representation to preserve their distinct feature spaces. Across ViT, Swin, and ConvNeXt architectures, LSF improves OOD detection across a range of evaluated settings, including near- and far-OOD and covariate shifts.