mlsanityData to 14 Oct 2026

SVD-Based Typicality Maps for Out-of-Distribution Detection in Vision Transformers

arXiv 2608.23499 ↗First posted 24 Aug 2026cs.CVcited by 0

On the map: Mechanistic interpretability → Interpreting vision and multimodal models

Abstract (arXiv)

We present a method for analyzing the internal representations of Vision Transformers (ViTs) exploiting the geometry of their learned parameters. Each affine layer's weight matrix is factored via Singular Value Decomposition (SVD), and activations are projected onto the leading right singular vectors to obtain compact, layer-intrinsic representations. A class-conditional density model is then fitted at each layer, producing per-class typicality scores that are stacked across depth into typicality maps: two-dimensional summaries of how class-specific evidence evolves through the network. From these maps, we derive two post-hoc scores for Out-Of-Distribution (OOD) detection: a Prototype Alignment Score (PAS), measuring agreement with class reference prototype patterns, and a Multi-Layer Soft Voting (MLSV) score, capturing cross-layer consensus without stored prototypes. On ViT-B/16 fine-tuned on CIFAR-100, the proposed scores achieve competitive detection performance without retraining or OOD exposure.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpreting vision and multimodal models, one of 13 directions in Mechanistic interpretability. Builds on 12 of its 18 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

12 of 18 references.

References · 12

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  3. 2013Describing Textures in the Wildcited by 2,125
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  8. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  9. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  10. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  11. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  12. 2025Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassificationscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Understanding vision transformer robustness through the lens of out-of-distribution detection
  2. 2026Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
  3. 2024SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis
  4. 2022Delving into Out-of-Distribution Detection with Vision-Language Representations
  5. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
  6. 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
  7. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
  8. 2025Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection