AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space

Siwon Kim, Jinoh Oh, Sungjin Lee, Seunghak Yu, Jaeyoung Do, Tara Taghavi

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 13 citations (OpenAlex)

Read the paper

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 text-driven CLIP concept directions instead of image-derived CAVsConceptual counterfactual explanations · AwA2 and CUBAUROC: 0.6436 -> 0.8132; 0.7066 -> 0.7891; 0.6113 -> 0.7314; 0.6979 -> 0.7750; 0.5811 -> 0.7316; 0.6811 -> 0.7336Improved
Vary concept prompt templates while preserving their meaning (ablation)CounTEX · Different prompt configurationsSpearman rank correlation of explanationsNo clear effect
Train projector and inverse projector with 50 rather than 10 images per class (ablation)CounTEX projection and inverse projection · ImageNet validationNMSE: 0.3394 -> 0.2834; 0.4370 -> 0.3399; 0.3871 -> 0.2606; 0.5928 -> 0.3544Improved
Train projector and inverse projector with the full ImageNet training set rather than 50 images per class (ablation)CounTEX projection and inverse projection · ImageNet validationNMSE: 0.2834 -> 0.2479; 0.3399 -> 0.3270; 0.2606 -> 0.2150; 0.3544 -> 0.2314Mixed

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