mlsanityData to 7 Oct 2026

GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection

arXiv 2311.09620 ↗First posted 16 Nov 2023cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data -- analyzing the uncertainty that arises when models attempt to explain their predictive decisions. This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns. Consequently, we investigate how attribution gradients lead to uncertain explanation outcomes and introduce two forms of abnormalities for OOD detection: the zero-deflation abnormality and the channel-wise average abnormality. We then propose GAIA, a simple and effective approach that incorporates Gradient Abnormality Inspection and Aggregation. The effectiveness of GAIA is validated on both commonly utilized (CIFAR) and large-scale (ImageNet-1k) benchmarks. Specifically, GAIA reduces the average FPR95 by 23.10% on CIFAR10 and by 45.41% on CIFAR100 compared to advanced post-hoc methods.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

33 of 42 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
21 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  3. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  11. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  12. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  13. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  14. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  15. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  16. 2020Deep Learning for Financial Applications : A Surveycited by 90
  17. 2020Gradients as a Measure of Uncertainty in Neural Networkscited by 55
  18. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  19. 2022Do Explanations Explain? Model Knows Bestcited by 20
  20. 2022How Useful are Gradients for OOD Detection Really?cited by 20
  21. 2023Understanding and Unifying Fourteen Attribution Methods with Taylor Interactionscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 3.

12 papers.

  1. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  2. 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveragingcited by 8
  3. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  4. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  5. 2024PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognitioncited by 2
  6. 2025GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detectioncited by 2
  7. 2025Activation Subspaces for Out-of-Distribution Detectioncited by 2
  8. 2026UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shiftscited by 1
  9. 2023GROOD: GRadient-Aware Out-of-Distribution Detectioncited by 0
  10. 2025Open Set Domain Adaptation with Vision-language models via Gradient-aware Separationcited by 0
  11. 2026The Invisible Gorilla Effect in Out-of-distribution Detectioncited by 0
  12. 2026Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detectioncited by 0