mlsanityData to 14 Oct 2026

AdaptGrad: Adaptive Sampling to Reduce Noise

arXiv 2410.07711 ↗First posted 10 Oct 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Gradient Smoothing is an efficient approach to reducing noise in gradient-based model explanation method. SmoothGrad adds Gaussian noise to mitigate much of these noise. However, the crucial hyper-parameter in this method, the variance σ of Gaussian noise, is set manually or with heuristic approach. However, it results in the smoothed gradients still containing a certain amount of noise. In this paper, we aim to interpret SmoothGrad as a corollary of convolution, thereby re-understanding the gradient noise and the role of σ from the perspective of confidence level. Furthermore, we propose an adaptive gradient smoothing method, AdaptGrad, based on these insights. Through comprehensive experiments, both qualitative and quantitative results demonstrate that AdaptGrad could effectively reduce almost all the noise in vanilla gradients compared with baselines methods. AdaptGrad is simple and universal, making it applicable for enhancing gradient-based interpretability methods for better visualization.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  10. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  11. 2018Sanity Checks for Saliency Mapscited by 1,156
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,109
33 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  3. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  6. 2017The (Un)reliability of saliency methodscited by 333
  7. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  8. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  9. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
  10. 2019Explanations can be manipulated and geometry is to blamecited by 216
  11. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  12. 2020Debugging Tests for Model Explanationscited by 147
  13. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 126
  14. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  15. 2019XRAI: Better Attributions Through Regionscited by 116
  16. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  17. 2019When Explanations Lie: Why Many Modified BP Attributions Failcited by 92
  18. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  19. 2018A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationscited by 60
  20. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  21. 2020SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localizationcited by 46
  22. 2022Rethinking Attention-Model Explainability through Faithfulness Violation Testcited by 43
  23. 2020Smoothed Geometry for Robust Attributioncited by 38
  24. 2022Transferable Adversarial Attack based on Integrated Gradientscited by 35
  25. 2018Towards Explanation of DNN-based Prediction with Guided Feature Inversioncited by 31
  26. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  27. 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attributioncited by 21
  28. 2019A study on the Interpretability of Neural Retrieval Models using DeepSHAPcited by 19
  29. 2023Visual Explanations via Iterated Integrated Attributionscited by 19
  30. 2020Learning outside the Black-Box: The pursuit of interpretable modelscited by 18
  31. 2023IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradientscited by 16
  32. 2020DANCE: Enhancing saliency maps using decoyscited by 10
  33. 2022A Psychological Theory of Explainabilitycited by 10

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025Value bounds and Convergence Analysis for Averages of LRP attributionscited by 0
  2. 2026Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecastingcited by 0