mlsanityData to 14 Oct 2026

Early High-Frequency Injection for Geometry-Sensitive OOD Detection

arXiv 2605.20728 ↗First posted 20 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2013Describing Textures in the Wildcited by 2,125
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
33 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  2. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2018On the Spectral Bias of Neural Networkscited by 1,341
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  6. 2019Contrastive Multiview Codingcited by 1,301
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  11. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  12. 2020Contrastive Learning with Hard Negative Samplescited by 628
  13. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  14. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  15. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  16. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  17. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  18. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  19. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 368
  20. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  21. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  22. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  23. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  24. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  25. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  26. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  27. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  28. 2023Non-Parametric Outlier Synthesiscited by 129
  29. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  30. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  31. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  32. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  33. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23

Built on by

Not cited yet.