Research map / Label-efficient and robust learning / Recognition and long-tail
SCOUT: Self-Aware Discriminant Counterfactual Explanations
Pei Wang, Nuno Vasconcelos
Check 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 |
|---|---|---|---|
| Replace exhaustive feature matching with SCOUT counterfactual explanations | Goyal method · CUB200, beginner, VGG16 | recall: 0.02 (0.01) -> 0.05 (0.01) | Improved |
| Replace exhaustive feature matching with SCOUT counterfactual explanations | Goyal method · CUB200, advanced, VGG16 | recall: 0.05 (0.00) -> 0.05 (0.00) | No clear effect |
| Replace exhaustive feature matching with SCOUT counterfactual explanations | Goyal method · CUB200, ResNet-50 | PIoU: 0.18 (0.01) -> 0.16 (0.01); 0.15 (0.00) -> 0.15 (0.01) | Mixed |
| Replace exhaustive feature matching with SCOUT counterfactual explanations | Goyal method · CUB200, beginner, VGG16 | IPS: 0.02 (0.00) -> 26.51 (0.71) | Improved |
| Replace exhaustive feature matching with SCOUT counterfactual explanations | Goyal method · CUB200, beginner, ResNet-50 | IPS: 1.13 (0.07) -> 78.54 (11.87) | Improved |
| Add the discriminant map combining prediction, counter-class, and confidence attributions (ablation) | Attributive explanations · CUB200, beginner and advanced users | localization performance | Improved |
| Use the easiness score for the confidence attribution (ablation) | SCOUT discriminant explanations · CUB200 | localization performance | Improved |
| Use self-awareness through confidence attribution (ablation) | SCOUT discriminant explanations · CUB200, especially advanced users | localization performance | Improved |
| Provide SCOUT counterfactual feedback instead of random highlighted regions | Human machine teaching · Bird classification | mean accuracy: 60% -> 95% | Improved |
| Provide SCOUT counterfactual feedback instead of lighting the entire images | Human machine teaching · Bird classification | mean accuracy: 77% -> 95% | Improved |
Later papers that compared with this method
2 later accepted papers report SCOUT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition (CVPR 2025 · better on 0 of 1 shared result)
- Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals (ECCV 2022 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Counterfactual Visual Explanations (ICML 2019 · similarity 0.90)
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · similarity 0.88)
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint) (AAAI 2024 · similarity 0.88)
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · similarity 0.86)
- Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition (CVPR 2025 · similarity 0.86)
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching (NeurIPS 2025 · 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.
