mlsanityData to 7 Oct 2026

Valid P-Value for Deep Learning-Driven Salient Region

arXiv 2301.02437 ↗First posted 6 Jan 2023stat.ML cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Various saliency map methods have been proposed to interpret and explain predictions of deep learning models. Saliency maps allow us to interpret which parts of the input signals have a strong influence on the prediction results. However, since a saliency map is obtained by complex computations in deep learning models, it is often difficult to know how reliable the saliency map itself is. In this study, we propose a method to quantify the reliability of a salient region in the form of p-values. Our idea is to consider a salient region as a selected hypothesis by the trained deep learning model and employ the selective inference framework. The proposed method can provably control the probability of false positive detections of salient regions. We demonstrate the validity of the proposed method through numerical examples in synthetic and real datasets. Furthermore, we develop a Keras-based framework for conducting the proposed selective inference for a wide class of CNNs without additional implementation cost.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 6 Jan 2023.

Builds on

34 of 42 references.

References · 34

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  7. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  8. 2015Automatic differentiation in machine learning: a surveycited by 846
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  10. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  11. 2017Interpretation of Neural Networks is Fragilecited by 443
  12. 2014Understanding Deep Image Representations by Inverting Themcited by 399
22 more
  1. 2017The (Un)reliability of saliency methodscited by 331
  2. 2019Explanations can be manipulated and geometry is to blamecited by 215
  3. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  4. 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
  5. 2013Exact post-selection inference, with application to the lassocited by 90
  6. 2019Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithmcited by 76
  7. 2018Interpretable Deep Learning under Firecited by 74
  8. 2014Exact Post-Selection Inference for Sequential Regression Procedurescited by 47
  9. 2017Valid Inference Corrected for Outlier Removalcited by 25
  10. 2020Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programmingcited by 25
  11. 2019Computing Valid p-values for Image Segmentation by Selective Inferencecited by 24
  12. 2021More Powerful Conditional Selective Inference for Generalized Lasso by Parametric Programmingcited by 24
  13. 2018More powerful post-selection inference, with application to the Lassocited by 22
  14. 2016Selective Inference for Group-Sparse Linear Modelscited by 21
  15. 2020Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inferencecited by 21
  16. 2018Post-Selection Inference for Changepoint Detection Algorithms with Application to Copy Number Variation Datacited by 19
  17. 2015Selective Sequential Model Selectioncited by 16
  18. 2021Conditional Selective Inference for Robust Regression and Outlier Detection using Piecewise-Linear Homotopy Continuationcited by 16
  19. 2021Fast and More Powerful Selective Inference for Sparse High-order Interaction Modelcited by 15
  20. 2021Valid and Exact Statistical Inference for Multi-dimensional Multiple Change-Points by Selective Inferencecited by 10
  21. 2016Integrative Methods for Post-Selection Inference Under Convex Constraintscited by 7
  22. 2020More Powerful and General Selective Inference for Stepwise Feature Selection using the Homotopy Continuation Approachcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 5; 2026: 3.

17 papers.

Sort:

  1. 2023CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inferencecited by 10
  2. 2024Statistical Test for Attention Map in Vision Transformercited by 6
  3. 2024Statistical Test for Anomaly Detections by Variational Auto-Encoderscited by 6
  4. 2023Selective Inference for Changepoint detection by Recurrent Neural Networkcited by 4
  5. 2024Statistical Test for Auto Feature Engineering by Selective Inferencecited by 3
  6. 2025Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inferencecited by 3
  7. 2024Controllable RANSAC-based Anomaly Detection via Hypothesis Testingcited by 2
  8. 2025Change Point Detection in the Frequency Domain with Statistical Reliabilitycited by 2
  9. 2025Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptationcited by 2
  10. 2023Bounded P-values in Parametric Programming-based Selective Inferencecited by 1
  11. 2024Statistical Test for Diffusion-Based Anomaly Localization via Selective Inferencecited by 1
  12. 2025Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inferencecited by 1
5 more
  1. 2024Statistical testing on generative AI anomaly detection tools in Alzheimer's Disease diagnosiscited by 0
  2. 2025Statistical Inference for Clustering-based Anomaly Detectioncited by 0
  3. 2026Automatic Statistical Test for Rationally Expressible Algorithms by Selective Inference, with Applications to Feature Selectioncited by 0
  4. 2026Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathologycited by 0
  5. 2026Post-Anomaly Detection Inference for Deep SVDDcited by 0