Research map / Label-efficient and robust learning / Recognition and long-tail
On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use PIECE's exceptional-feature replacement instead of CEM | CNN counterfactual explanations · MNIST | MC Mean: 0.62 -> 0.99 | Helped |
| Use PIECE's exceptional-feature replacement instead of CEM | CNN counterfactual explanations · MNIST | NN-Dist: 0.99 -> 0.41 | Helped |
| Use PIECE's exceptional-feature replacement instead of Proto-CF | CNN counterfactual explanations · MNIST | IM1: 1.28 -> 0.72 | Helped |
| Use PIECE's exceptional-feature replacement instead of CEM | CNN counterfactual explanations · MNIST | R%-Sub: 43.87 -> 69.32 | Helped |
| Use PIECE's exceptional-feature replacement instead of Min-Edit | CNN counterfactual explanations · CIFAR-10 | MC Mean: 0.61 -> 0.96 | Helped |
| Use PIECE's exceptional-feature replacement instead of Min-Edit | CNN counterfactual explanations · CIFAR-10 | NN-Dist: 1.48 -> 1.17 | Helped |
| Use PIECE's exceptional-feature replacement instead of Min-Edit | CNN counterfactual explanations · CIFAR-10 | IM1: 1.17 -> 1.15 | Helped |
| Generate semi-factuals by modifying exceptional features and stopping before the decision boundary | PIECE · MNIST | L1 pixel distance | Helped |
| Increase the proportion of exceptional features modified (ablation) | PIECE semi-factuals · MNIST | MC-Dropout plausibility | Mixed |
Closest papers by meaning
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint) (AAAI 2024 · similarity 0.91)
- V-CECE: Visual Counterfactual Explanations via Conceptual Edits (NeurIPS 2025 · similarity 0.89)
- Semi-factual Explanations in AI (AAAI 2024 · similarity 0.87)
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching (NeurIPS 2025 · similarity 0.87)
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · similarity 0.87)
- Promoting Counterfactual Robustness through Diversity (AAAI 2024 · similarity 0.87)
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.