mlsanityData to 7 Oct 2026

Two-Stage Holistic and Contrastive Explanation of Image Classification

arXiv 2306.06339 ↗First posted 10 Jun 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The need to explain the output of a deep neural network classifier is now widely recognized. While previous methods typically explain a single class in the output, we advocate explaining the whole output, which is a probability distribution over multiple classes. A whole-output explanation can help a human user gain an overall understanding of model behaviour instead of only one aspect of it. It can also provide a natural framework where one can examine the evidence used to discriminate between competing classes, and thereby obtain contrastive explanations. In this paper, we propose a contrastive whole-output explanation (CWOX) method for image classification, and evaluate it using quantitative metrics and through human subject studies. The source code of CWOX is available at https://github.com/vaynexie/CWOX.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 10 Jun 2023.

Builds on

32 of 44 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2014Going Deeper with Convolutionscited by 4,231
  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. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  10. 2018Sanity Checks for Saliency Mapscited by 1,149
  11. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  12. 2014Striving for Simplicity: The All Convolutional Netcited by 983
20 more
  1. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  2. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  3. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  4. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  5. 2019Counterfactual Visual Explanationscited by 312
  6. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  7. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
  8. 2017Interpretable Convolutional Neural Networkscited by 161
  9. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  10. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  11. 2019An Evaluation of the Human-Interpretability of Explanationcited by 71
  12. 2023Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision supportcited by 65
  13. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  14. 2020SCOUT: Self-aware Discriminant Counterfactual Explanationscited by 52
  15. 2020A systematic review and taxonomy of explanations in decision support and recommender systemscited by 45
  16. 2019Generative Counterfactual Introspection for Explainable Deep Learningcited by 36
  17. 2020Contrastive Explanations in Neural Networkscited by 26
  18. 2021Dissonance Between Human and Machine Understandingcited by 18
  19. 2016Latent Tree Models for Hierarchical Topic Detectioncited by 6
  20. 2016Latent Tree Analysiscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Free Argumentative Exchanges for Explaining Image Classifierscited by 3
  2. 2025Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partitioncited by 2
  3. 2025Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanationscited by 2
  4. 2025CASE: Contrastive Activation for Class-Sensitive Explanationscited by 0