AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SCOUT: Self-Aware Discriminant Counterfactual Explanations

Pei Wang, Nuno Vasconcelos

CVPR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 82 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace exhaustive feature matching with SCOUT counterfactual explanationsGoyal method · CUB200, beginner, VGG16recall: 0.02 (0.01) -> 0.05 (0.01)Improved
Replace exhaustive feature matching with SCOUT counterfactual explanationsGoyal method · CUB200, advanced, VGG16recall: 0.05 (0.00) -> 0.05 (0.00)No clear effect
Replace exhaustive feature matching with SCOUT counterfactual explanationsGoyal method · CUB200, ResNet-50PIoU: 0.18 (0.01) -> 0.16 (0.01); 0.15 (0.00) -> 0.15 (0.01)Mixed
Replace exhaustive feature matching with SCOUT counterfactual explanationsGoyal method · CUB200, beginner, VGG16IPS: 0.02 (0.00) -> 26.51 (0.71)Improved
Replace exhaustive feature matching with SCOUT counterfactual explanationsGoyal method · CUB200, beginner, ResNet-50IPS: 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 userslocalization performanceImproved
Use the easiness score for the confidence attribution (ablation)SCOUT discriminant explanations · CUB200localization performanceImproved
Use self-awareness through confidence attribution (ablation)SCOUT discriminant explanations · CUB200, especially advanced userslocalization performanceImproved
Provide SCOUT counterfactual feedback instead of random highlighted regionsHuman machine teaching · Bird classificationmean accuracy: 60% -> 95%Improved
Provide SCOUT counterfactual feedback instead of lighting the entire imagesHuman machine teaching · Bird classificationmean 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy