mlsanityData to 14 Oct 2026

V-CECE: Visual Counterfactual Explanations via Conceptual Edits

arXiv 2509.16567 ↗First posted 20 Sep 2025cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent black-box counterfactual generation frameworks fail to take into account the semantic content of the proposed edits, while relying heavily on training to guide the generation process. We propose a novel, plug-and-play black-box counterfactual generation framework, which suggests step-by-step edits based on theoretical guarantees of optimal edits to produce human-level counterfactual explanations with zero training. Our framework utilizes a pre-trained image editing diffusion model, and operates without access to the internals of the classifier, leading to an explainable counterfactual generation process. Throughout our experimentation, we showcase the explanatory gap between human reasoning and neural model behavior by utilizing both Convolutional Neural Network (CNN), Vision Transformer (ViT) and Large Vision Language Model (LVLM) classifiers, substantiated through a comprehensive human evaluation.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 20 Sep 2025.

Builds on

28 of 41 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  7. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  8. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  9. 2023A Comprehensive Overview of Large Language Modelscited by 648
  10. 2019Counterfactual Visual Explanationscited by 313
  11. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 310
  12. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
16 more
  1. 2022Diffusion Visual Counterfactual Explanationscited by 96
  2. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  3. 2022Diffusion Models for Counterfactual Explanationscited by 79
  4. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  5. 2023Adversarial Counterfactual Visual Explanationscited by 47
  6. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  7. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  8. 2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
  9. 2020Semantics and explanation: why counterfactual explanations produce adversarial examples in deep neural networkscited by 24
  10. 2023Learning Data Representations with Joint Diffusion Modelscited by 22
  11. 2023Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoningcited by 22
  12. 2024Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Modelscited by 18
  13. 2023Latent Diffusion Counterfactual Explanationscited by 17
  14. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14
  15. 2023Choose your Data Wisely: A Framework for Semantic Counterfactualscited by 7
  16. 2024Structure Your Data: Towards Semantic Graph Counterfactualscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanationscited by 0
  2. 2026Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliencycited by 0
  3. 2026SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networkscited by 0
  4. 2026GFGE: Unifying Explainable AI Methods through an Interpretation Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Concept-based Visual Counterfactual Explanations with Diffusion Models
  2. 2023Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation
  3. 2026EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing
  4. 2025Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding
  5. 2025From Visual Explanations to Counterfactual Explanations with Latent Diffusion
  6. 2025Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
  7. 2026FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations
  8. 2026Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model