Early High-Frequency Injection for Geometry-Sensitive OOD Detection
Abstract
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.
Cite
@article{arxiv.2605.20728,
title = {Early High-Frequency Injection for Geometry-Sensitive OOD Detection},
author = {Chuanjie Cheng and Ningkang Peng and Chenxi Liu and Yifan He and Peirong Ma and Yanhui Gu},
journal= {arXiv preprint arXiv:2605.20728},
year = {2026}
}