mlsanityData to 14 Oct 2026

MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion

arXiv 2606.17352 ↗First posted 15 Jun 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce MM++ (Multilayer Mahalanobis++), a strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection. To address the trade-off between scale invariance and hierarchical expressivity, MM++ constructs a principled joint feature space. It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression. By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise. Crucially, a Ledoit-Wolf regularized tied covariance matrix stabilizes this unified space, enabling reliable distance estimation. Requiring no auxiliary OOD data, classifier fine-tuning, or architectural modifications, MM++ delivers robust performance across distinct architectures for both near- and far-OOD detection.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 48 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

41 of 48 references.

References · 41

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2013Describing Textures in the Wildcited by 2,125
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  9. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  11. 2019Natural Adversarial Examplescited by 1,408
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
29 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  2. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  3. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  4. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  5. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  7. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  8. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2023EVA-02: A Visual Representation for Neon Genesiscited by 381
  11. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 341
  12. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  13. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  14. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  15. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  16. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  17. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  18. 2023Non-Parametric Outlier Synthesiscited by 129
  19. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  20. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  21. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  22. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 32
  23. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  24. 2021ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networkscited by 24
  25. 2023On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imagingcited by 15
  26. 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learningcited by 11
  27. 2025A Geometry-Based View of Mahalanobis OOD Detectioncited by 4
  28. 2023Exploring Simple, High Quality Out-of-Distribution Detection with L2 Normalizationcited by 3
  29. 2026AP-OOD: Attention Pooling for Out-of-Distribution Detectioncited by 1

Built on by

Not cited yet.