mlsanityData to 7 Oct 2026

Block Selection Method for Using Feature Norm in Out-of-distribution Detection

arXiv 2212.02295 ↗First posted 5 Dec 2022cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Detecting out-of-distribution (OOD) inputs during the inference stage is crucial for deploying neural networks in the real world. Previous methods commonly relied on the output of a network derived from the highly activated feature map. In this study, we first revealed that a norm of the feature map obtained from the other block than the last block can be a better indicator of OOD detection. Motivated by this, we propose a simple framework consisting of FeatureNorm: a norm of the feature map and NormRatio: a ratio of FeatureNorm for ID and OOD to measure the OOD detection performance of each block. In particular, to select the block that provides the largest difference between FeatureNorm of ID and FeatureNorm of OOD, we create Jigsaw puzzle images as pseudo OOD from ID training samples and calculate NormRatio, and the block with the largest value is selected. After the suitable block is selected, OOD detection with the FeatureNorm outperforms other OOD detection methods by reducing FPR95 by up to 52.77% on CIFAR10 benchmark and by up to 48.53% on ImageNet benchmark. We demonstrate that our framework can generalize to various architectures and the importance of block selection, which can improve previous OOD detection methods as well.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 49 of its 67 references that are in the map. First posted on arXiv 5 Dec 2022.

Builds on

49 of 67 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2016Wide Residual Networkscited by 3,057
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
37 more
  1. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  9. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  10. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  11. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  12. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  13. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  14. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  15. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  16. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  17. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  18. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  19. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  20. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  21. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  22. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  23. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  24. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  25. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  26. 2018Reducing Network Agnostophobiacited by 165
  27. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  28. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  29. 2020Calibration of Neural Networks using Splinescited by 97
  30. 2017L2-constrained Softmax Loss for Discriminative Face Verificationcited by 96
  31. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  32. 2021Soft Calibration Objectives for Neural Networkscited by 89
  33. 2019Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classificationcited by 57
  34. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  35. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  36. 2020Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examplescited by 16
  37. 2022A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptionscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 11; 2025: 10; 2026: 1.

30 papers.

Sort:

By area:

  1. 2024Kernel PCA for Out-of-Distribution Detectioncited by 24
  2. 2023VRA: Variational Rectified Activation for Out-of-distribution Detectioncited by 15
  3. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  4. 2023Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspectivecited by 10
  5. 2024Out-of-Distribution Detection via Deep Multi-Comprehension Ensemblecited by 8
  6. 2024Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptationcited by 8
  7. 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveragingcited by 8
  8. 2024A Layer Selection Approach to Test Time Adaptationcited by 7
  9. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  10. 2024OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learningcited by 7
  11. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5
  12. 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptationcited by 4
18 more
  1. 2025H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detectioncited by 4
  2. 2023Exploring Simple, High Quality Out-of-Distribution Detection with L2 Normalizationcited by 3
  3. 2025Enhancing Out-of-Distribution Detection with Extended Logit Normalizationcited by 3
  4. 2025FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detectioncited by 3
  5. 2023Hidden Conflicts in Neural Networks and Their Implications for Explainabilitycited by 2
  6. 2024Out-of-Distribution Detection using Neural Activation Priorcited by 2
  7. 2024TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learningcited by 2
  8. 2024Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learningcited by 1
  9. 2025Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximationcited by 1
  10. 2025BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapsecited by 1
  11. 2023SupEuclid: Extremely Simple, High Quality OoD Detection with Supervised Contrastive Learning and Euclidean Distancecited by 0
  12. 2023Distilling the Unknown to Unveil Certaintycited by 0
  13. 2024Hallucination Detection in Virtually-Stained Histology: A Latent Space Baselinecited by 0
  14. 2025Unsupervised Out-of-Distribution Detection in Medical Imaging Using Multi-Exit Class Activation Maps and Feature Maskingcited by 0
  15. 2025Out-of-Distribution Detection with Adaptive Top-K Logits Integrationcited by 0
  16. 2025Local Background Features Matter in Out-of-Distribution Detectioncited by 0
  17. 2025Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detectioncited by 0
  18. 2026Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detectioncited by 0