mlsanityData to 7 Oct 2026

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain

arXiv 2305.14979 ↗First posted 24 May 2023cs.CV cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: urlhttps://github.com/gabrielkasmi/spectral-attribution.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 40 of its 62 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

40 of 62 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
28 more
  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  4. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2018On the Spectral Bias of Neural Networkscited by 1,321
  8. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  9. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  10. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 360
  11. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  12. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  13. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  14. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
  15. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  16. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  17. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  18. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  19. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  20. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
  21. 2022Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysiscited by 38
  22. 2018Modeling Sparse Deviations for Compressed Sensing using Generative Modelscited by 33
  23. 2022Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measurecited by 33
  24. 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
  25. 2019Tutorial: Safe and Reliable Machine Learningcited by 22
  26. 2021White Paper Machine Learning in Certified Systemscited by 15
  27. 2022A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadatacited by 9
  28. 2021Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodologycited by 4

Built on by

Cited by year

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

5 papers.

  1. 2024Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systemscited by 4
  2. 2024Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwavescited by 4
  3. 2024One Wave To Explain Them All: A Unifying Perspective On Feature Attributioncited by 3
  4. 2023Can We Reliably Improve the Robustness to Image Acquisition of Remote Sensing of PV Systems?cited by 2
  5. 2025FREQuency ATTribution: benchmarking frequency-based occlusion for time series datacited by 0