Research map / Vision-language and multimodal / Human and embodied modeling
Counterfactual Visual Explanations
Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, Stefan Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Provide counterfactual visual explanations in addition to training examples | Human learners classifying CUB 2011 birds · CUB 2011 human teaching test | human test accuracy: 71.09\% -> 78.77\% | Improved |
| Replace no-explanation feedback with GradCAM feedback | Human learners classifying CUB 2011 birds · CUB 2011 human teaching test | human test accuracy: 71.09\% -> 74.29\% | Improved |
| Use counterfactual feedback instead of GradCAM feedback | Human learners classifying CUB 2011 birds · CUB 2011 human teaching test | human test accuracy: 74.29\% -> 78.77\% | No clear effect |
| Provide counterfactual visual explanations as training feedback | Human learners without ML knowledge · CUB 2011 human teaching test, participants without ML knowledge | human test accuracy: 61.7\% -> 72.4\% | Improved |
| Use continuous relaxation instead of exhaustive search | Counterfactual visual explanation generation · CUB 2011 | exact solution agreement with exhaustive search: 79.98\%; 92\% | Mixed |
| Choose a nearest-neighbor attribute distractor class instead of a random distractor class | Counterfactual visual explanations · CUB 2011 | edits to change model prediction: 7.4 -> 5.3 | Improved |
Closest papers by meaning
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · similarity 0.90)
- Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition (CVPR 2025 · similarity 0.89)
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint) (AAAI 2024 · similarity 0.89)
- V-CECE: Visual Counterfactual Explanations via Conceptual Edits (NeurIPS 2025 · similarity 0.88)
- Structure Your Data: Towards Semantic Graph Counterfactuals (ICML 2024 · similarity 0.87)
- CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
