Early High-Frequency Injection for Geometry-Sensitive OOD Detection
About
Post-hoc OOD detectors score logits or features after training, so their success depends on the geometry already encoded in the representation. We revisit this assumption through a band-wise MMD^2 analysis across CE, SimCLR, SupCon, and the OOD-oriented representation method PALM. In our diagnostic, low-frequency input bands induce weaker ID/OOD feature discrepancy, whereas higher-frequency bands tend to provide stronger separability. This observation motivates EIHF, an input-side intervention that exposes high-frequency evidence before the first convolution without changing the training objective. EIHF is strongest for geometry-sensitive OOD detection: under matched training and scoring settings, it reshapes class-conditional feature geometry and reduces ID/OOD Mahalanobis score overlap. Experiments on CIFAR-100 and ImageNet-100 show gains on CIFAR-100 and the best average FPR95 with second-best average AUROC on ImageNet-100, while also revealing a limitation on the scene-centric Places shift. Code is available at https://anonymous.4open.science/r/EIHF.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| OOD Detection | CIFAR-100 vs ISUN (test) | FPR @ 0.05 FNR14.14 | 41 | |
| OOD Detection | CIFAR-100 LSUN IND R OOD | AUROC97.59 | 38 | |
| OOD Detection | CIFAR-10 | FPR95 (SVHN)1.36 | 36 | |
| OOD Detection | ImageNet-100 (ID) vs TEXTURES (OOD) | AUROC99.58 | 33 | |
| Out-of-Distribution Detection | CIFAR100 (ID) vs SVHN (OOD) | AUROC0.9908 | 33 | |
| Out-of-distribution (OOD) detection | CIFAR100 In-Distribution Place365 Out-of-Distribution (test) | AUROC83.46 | 29 | |
| OOD Detection | CIFAR-100 OOD (Average of SVHN, Places365, LSUN, iSUN, Textures) | FPR@9525.73 | 14 | |
| OOD Detection | CIFAR-100 (In-distribution) vs Textures (OOD) | FPR9538.78 | 14 | |
| OOD Detection | ImageNet100 (In-distribution) vs SUN (OOD) (test) | FPR@9523.83 | 14 | |
| OOD Detection | ImageNet-100 | Avg FPR9552.03 | 14 |