mlsanityData to 7 Oct 2026

How to train your ViT for OOD Detection

arXiv 2405.17447 ↗First posted 21 May 2024cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

VisionTransformers have been shown to be powerful out-of-distribution detectors for ImageNet-scale settings when finetuned from publicly available checkpoints, often outperforming other model types on popular benchmarks. In this work, we investigate the impact of both the pretraining and finetuning scheme on the performance of ViTs on this task by analyzing a large pool of models. We find that the exact type of pretraining has a strong impact on which method works well and on OOD detection performance in general. We further show that certain training schemes might only be effective for a specific type of out-distribution, but not in general, and identify a best-practice training recipe.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 16 references that are in the map. First posted on arXiv 21 May 2024.

Builds on

15 of 16 references.

References · 15

  1. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  3. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  5. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  6. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  7. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  8. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  9. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  10. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  11. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  12. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
3 more
  1. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  2. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  3. 2023A framework for benchmarking class-out-of-distribution detection and its application to ImageNetcited by 31

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 30
  2. 2025A Geometry-Based View of Mahalanobis OOD Detectioncited by 4