AI Paper Atlas

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

CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines

Arjun Akula, Shuai Wang, Song-Chun Zhu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 72 citations (OpenAlex)

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 changedWhereMeasuredEffect
use CoCoX fault-line explanations instead of no explanationVGG-16 users · ImageNet 40 classes, non-expert poolJustified Trust: 21.4 % -> 69.1 %Improved
use CoCoX instead of no explanationVGG-16 users · ImageNet 40 classes, expert poolJustified Trust: 28.1 % -> 70.5 %Improved
use CoCoX instead of best baseline (CEM)non-expert users · ImageNet 40 classes, non-expert poolJustified Trust: 51.0 % -> 69.1 %Improved
use CoCoX instead of best baseline (CVE)expert users · ImageNet 40 classes, expert poolJustified Trust: 64.5 % -> 70.5 %Improved
use attention-map explanations (CAM, Grad-CAM, SmoothGrad) instead of no explanationnon-expert users · ImageNet 40 classes, non-expert poolJustified Trust: 21.4 % -> 29.2 % (Grad-CAM)No clear effect
use concept-based (TCAV) or counterfactual (CEM, CVE) explanations instead of no explanationusers · ImageNet 40 classes, non-expert poolJustified Trust: 21.4 % -> 49.7 % (TCAV)Improved
combine concepts with counterfactuals (CoCoX) versus LIME on explanation satisfaction usefulnessnon-expert users · ImageNet 40 classes, non-expert poolExplanation Satisfaction usefulness: 4.2 -> 6.6Improved
more sessions of familiarization and testingCoCoX group · non-expert pool over sessionsJustified TrustMixed

Later papers that compared with this method

1 later accepted paper reports CoCoX 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