AI Paper Atlas

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

CE-FAM: Concept-Based Explanation via Fusion of Activation Maps

Michihiro Kuroki, Toshihiko Yamasaki

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 2 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 similarity loss (multi-layer, CLIP) (ablation)CE-FAM ResNet50 · Broden NRA avgNRA: 0.338 -> 0.361Improved
use multiple layers (similarity loss, CLIP) (ablation)CE-FAM ResNet50 · Broden NRA avgNRA: 0.348 -> 0.361Improved
replace CLIP with SigLIP (both losses) (ablation)CE-FAM ResNet50 · Broden NRA avgNRA: 0.361 -> 0.388Improved
replace CLIP with SigLIP (both losses) (ablation)CE-FAM ResNet50 · Broden Hit Rate avgHit Rate: 0.247 -> 0.295Improved
add similarity loss with SigLIP, multi-layer (ablation)CE-FAM ResNet50 · Broden Hit Rate avgHit Rate: 0.283 -> 0.295Improved
use CE-FAM instead of CLIP-Dissect (ablation)ResNet50 · Broden Hit Rate avgHit Rate: 0.199 -> 0.247Improved
use CE-FAM instead of CLIP-Dissect (ablation)ViT-B/16 · Broden NRA avg (top-1)NRA: 0.105 -> 0.273Improved
use CE-FAM instead of CLIP-Dissect for color conceptsResNet50 · Broden Color NRANRA: 0.393 -> 0.294Hurt
use CE-FAM instead of WWWResNet18 · ImageNet-S NRANRA: 0.527 -> 0.492Hurt

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