AI Paper Atlas

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

Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance

Jung-Ho Hong, Woo-Jeoung Nam, Kyu-Sung Jeon, Seong-Whan Lee

AAAI 2023 · 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
Apply UCAG to GradCAMGradCAM on ImageNet with ResNet50 · ImageNetdeletion AUC: 11.3 -> 8.6Improved
Apply UCAG to GradCAMGradCAM on ImageNet with ResNet50 · ImageNetinsertion AUC: 53.9 -> 53.4No clear effect
Apply UCAG to GradCAM on VOC07GradCAM · VOC07 Testpointing game: 86.6/74.0 -> 91.1/82.8Improved
Apply UCAG to GradCAM on COCO14GradCAM · COCO14 Valpointing game: 54.2/49.0 -> 61.8/57.6Improved
Apply UCAG to GradCAMGradCAM on ImageNet segmentation with ResNet50 · ImageNet segmentationpositive map density: 2.33 -> 3.89Improved
Apply UCAG to GradCAMGradCAM on ImageNet segmentation with ResNet50 · ImageNet segmentationnegative map density: 0.86 -> 0.81Improved
Use image upscaling without spatial scrutiny (ablation)GradCAM on ImageNet · ImageNetdeletion AUCHurt
Use image upscaling without spatial scrutiny (ablation)GradCAM on ImageNet · ImageNetinsertion AUCHurt

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