mlsanityData to 7 Oct 2026

Contrastive Counterfactual Visual Explanations With Overdetermination

arXiv 2106.14556 ↗First posted 28 Jun 2021cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27% using a novel pointing game metric. CLEAR Image excels in identifying cases of "causal overdetermination" where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 29 of its 56 references that are in the map. First posted on arXiv 28 Jun 2021.

Builds on

29 of 56 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  9. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  10. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
17 more
  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  2. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  3. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  4. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  5. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  8. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  9. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  10. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  11. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  12. 2018GANs for Medical Image Analysiscited by 81
  13. 2018A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationscited by 59
  14. 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
  15. 2019Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localizationcited by 38
  16. 2020DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervisioncited by 13
  17. 2017Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 0; 2025: 1; 2026: 1.

7 papers.

  1. 2022ViT-CX: Causal Explanation of Vision Transformerscited by 27
  2. 2023GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanationscited by 17
  3. 2023FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Seriescited by 5
  4. 2021Counterfactual Instances Explain Littlecited by 1
  5. 2023Predicting recovery following stroke: deep learning, multimodal data and feature selection using explainable AIcited by 1
  6. 2025Opening the black box of deep learning: Validating the statistical association between explainable artificial intelligence (XAI) and clinical domain knowledge in fundus image-based glaucoma diagnosiscited by 0
  7. 2026The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learningcited by 0