mlsanityData to 14 Oct 2026

WeiPer: OOD Detection using Weight Perturbations of Class Projections

arXiv 2405.17164 ↗First posted 27 May 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent advances in out-of-distribution (OOD) detection on image data show that pre-trained neural network classifiers can separate in-distribution (ID) from OOD data well, leveraging the class-discriminative ability of the model itself. Methods have been proposed that either use logit information directly or that process the model's penultimate layer activations. With "WeiPer", we introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input. We show that this simple trick can improve the OOD detection performance of a variety of methods and additionally propose a distance-based method that leverages the properties of the augmented WeiPer space. We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework, especially pronounced in difficult settings in which OOD samples are positioned close to the training set distribution. We support our findings with theoretical motivations and empirical observations, and run extensive ablations to provide insights into why WeiPer works.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

32 of 45 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2016Concrete Problems in AI Safetycited by 1,642
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  9. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  10. 2015Towards Open Set Deep Networkscited by 538
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
20 more
  1. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  2. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  3. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  4. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  5. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  6. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  7. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
  8. 2019Subspace Robust Wasserstein Distancescited by 90
  9. 2018Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusionscited by 77
  10. 2020Distributional Sliced-Wasserstein and Applications to Generative Modelingcited by 69
  11. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 65
  12. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  13. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  14. 2021No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasetscited by 31
  15. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  16. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  17. 2022Back to the Basics: Revisiting Out-of-Distribution Detection Baselinescited by 16
  18. 2023How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?cited by 15
  19. 2017On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbationscited by 14
  20. 2020Adversarial Weight Perturbation Helps Robust Generalizationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  2. 2025Activation Subspaces for Out-of-Distribution Detectioncited by 2
  3. 2025COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIPcited by 0
  4. 2026The Invisible Gorilla Effect in Out-of-distribution Detectioncited by 0