mlsanityData to 7 Oct 2026

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

arXiv 2310.00227 ↗First posted 30 Sep 2023cs.CVcited by 77

Not on the map. Why?

Abstract (arXiv)

The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important. In this paper, we offer insights and analyses of recent state-of-the-art out-of-distribution (OOD) detection methods - extremely simple activation shaping (ASH). We demonstrate that activation pruning has a detrimental effect on OOD detection, while activation scaling enhances it. Moreover, we propose SCALE, a simple yet effective post-hoc network enhancement method for OOD detection, which attains state-of-the-art OOD detection performance without compromising in-distribution (ID) accuracy. By integrating scaling concepts into the training process to capture a sample's ID characteristics, we propose Intermediate Tensor SHaping (ISH), a lightweight method for training time OOD detection enhancement. We achieve AUROC scores of +1.85% for near-OOD and +0.74% for far-OOD datasets on the OpenOOD v1.5 ImageNet-1K benchmark. Our code and models are available at https://github.com/kai422/SCALE.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 30 Sep 2023.

Builds on

27 of 41 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  9. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  10. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  11. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  12. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
15 more
  1. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  3. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  4. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  5. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  6. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  7. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  8. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  9. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  10. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  11. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  12. 2022The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformerscited by 121
  13. 2023SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformercited by 60
  14. 2022GACT: Activation Compressed Training for Generic Network Architecturescited by 31
  15. 2022DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Trainingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 16; 2025: 32; 2026: 27.

77 papers.

Sort:

By area:

  1. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  2. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 33
  3. 2024Kernel PCA for Out-of-Distribution Detectioncited by 24
  4. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  5. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Modelscited by 21
  6. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  7. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  8. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  9. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  10. 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveragingcited by 8
  11. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  12. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
38 more
  1. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  2. 2025Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detectioncited by 4
  3. 2025Improving Out-of-Distribution Detection via Dynamic Covariance Calibrationcited by 4
  4. 2025A Geometry-Based View of Mahalanobis OOD Detectioncited by 4
  5. 2024Logit Scaling for Out-of-Distribution Detectioncited by 3
  6. 2025TS-OOD: Evaluating Time-Series Out-of-Distribution Detection and Prospective Directions for Progresscited by 3
  7. 2025Enhancing Out-of-Distribution Detection with Extended Logit Normalizationcited by 3
  8. 2024Out-of-Distribution Detection using Neural Activation Priorcited by 2
  9. 2024Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectorscited by 2
  10. 2024Improving Out-of-Distribution Detection by Combining Existing Post-hoc Methodscited by 2
  11. 2024Out-of-Distribution Detection with Relative Anglescited by 2
  12. 2024Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generationcited by 2
  13. 2025OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensingcited by 2
  14. 2025Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigmcited by 2
  15. 2025STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainabilitycited by 2
  16. 2025Buffer-free Class-Incremental Learning with Out-of-Distribution Detectioncited by 2
  17. 2025Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detectioncited by 2
  18. 2025Activation Subspaces for Out-of-Distribution Detectioncited by 2
  19. 2026Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Modelscited by 2
  20. 2025DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detectioncited by 1
  21. 2025GHOST: Gaussian Hypothesis Open-Set Techniquecited by 1
  22. 2025Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flowscited by 1
  23. 2025Advancing Out-of-Distribution Detection via Local Neuroplasticitycited by 1
  24. 2025Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximationcited by 1
  25. 2025Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectorscited by 1
  26. 2025Nearest-Class Mean and Logits Agreement for Wildlife Open-Set Recognitioncited by 1
  27. 2025Domain Feature Collapse: Implications for Out-of-Distribution Detection and Solutionscited by 1
  28. 2025Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarkingcited by 1
  29. 2026ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Researchcited by 1
  30. 2026One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detectioncited by 1
  31. 2026AP-OOD: Attention Pooling for Out-of-Distribution Detectioncited by 1
  32. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1
  33. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1
  34. 2026MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapsecited by 1
  35. 2024Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detectioncited by 0
  36. 2024Revisiting Energy-Based Model for Out-of-Distribution Detectioncited by 0
  37. 2025A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detectioncited by 0
  38. 2025LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layerscited by 0

50 most cited of 77 All 77 (JSON)