AI Paper Atlas

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

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li, Tomas Pfister, Pradeep K. Ravikumar

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 49 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
add the completeness objective to concept discovery (ablation)concept discovery method · synthetic and AwAcompleteness scoreImproved
use completeness-aware concept discovery instead of PCA/k-means/ACEconcept discovery · synthetic shapes user studycorrect concepts retrieved: 3.875 -> 5.0Improved
use completeness-aware method instead of PCAconcept discovery · AwA human studyaverage correct ratio: 0.267 -> 0.733Improved
use completeness-aware method instead of k-meansconcept discovery · synthetic shapesautomated alignment: 0.864 -> 0.98Improved
append random nearest neighbors of concept 4 (positive) instead of nothingIMDB CNN · IMDBaverage prediction score: 0.516 -> 0.678Improved

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