mlsanityData to 7 Oct 2026

Contrastive Explanations in Neural Networks

arXiv 2008.00178 ↗First posted 1 Aug 2020cs.CV cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of the form `Why P?'. These Why questions operate under broad contexts thereby providing answers that are irrelevant in some cases. We propose to constrain these Why questions based on some context Q so that our explanations answer contrastive questions of the form `Why P, rather than Q?'. In this paper, we formalize the structure of contrastive visual explanations for neural networks. We define contrast based on neural networks and propose a methodology to extract defined contrasts. We then use the extracted contrasts as a plug-in on top of existing `Why P?' techniques, specifically Grad-CAM. We demonstrate their value in analyzing both networks and data in applications of large-scale recognition, fine-grained recognition, subsurface seismic analysis, and image quality assessment.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 8; 2023: 5; 2024: 4; 2025: 3; 2026: 1.

26 papers.

Sort:

  1. 2021Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networkscited by 48
  2. 2021Towards Relatable Explainable AI with the Perceptual Processcited by 27
  3. 2022OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semanticscited by 23
  4. 2022Introspective Learning : A Two-Stage Approach for Inference in Neural Networkscited by 19
  5. 2022Attribution-based XAI Methods in Computer Vision: A Reviewcited by 16
  6. 2022Gradient-Based Adversarial and Out-of-Distribution Detectioncited by 14
  7. 2021Extracting Causal Visual Features for Limited label Classificationcited by 12
  8. 2021Contrastive Reasoning in Neural Networkscited by 11
  9. 2022Explanatory Paradigms in Neural Networkscited by 11
  10. 2023Gaussian Switch Sampling: A Second Order Approach to Active Learningcited by 10
  11. 2022Open-Set Recognition with Gradient-Based Representationscited by 7
  12. 2022Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanismcited by 7
14 more
  1. 2023Explaining Deep Models through Forgettable Learning Dynamicscited by 7
  2. 2024HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithmscited by 7
  3. 2025Hierarchical and Multimodal Data for Daily Activity Understandingcited by 6
  4. 2023Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretationcited by 4
  5. 2023Two-Stage Holistic and Contrastive Explanation of Image Classificationcited by 4
  6. 2024VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretabilitycited by 3
  7. 2023Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networkscited by 2
  8. 2024Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysiscited by 2
  9. 2024CRACKS: Crowdsourcing Resources for Analysis and Categorization of Key Subsurface faultscited by 2
  10. 2025Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partitioncited by 2
  11. 2022Explainable Machine Learning for Hydrocarbon Prospect Riskingcited by 1
  12. 2021VAE-CE: Visual Contrastive Explanation using Disentangled VAEscited by 0
  13. 2025Toward Simple and Robust Contrastive Explanations for Image Classification by Leveraging Instance Similarity and Concept Relevancecited by 0
  14. 2026Gradient based Severity Labeling for Biomarker Classification in OCTcited by 0