AI Paper Atlas

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

Shap-CAM: Visual Explanations for Convolutional Neural Networks Based on Shapley Value

Quan Zheng, Ziwei Wang, Jie Zhou, Jiwen Lu

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 64 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
replace Score-CAM with Shap-CAMVGG16 CAM · ImageNet valAverage Drop (%): 31.5 -> 28.0Improved
replace Score-CAM with Shap-CAMVGG16 CAM · ImageNet valAverage Increase in Confidence (%): 30.6 -> 31.8Improved
replace Score-CAM with Shap-CAMVGG16 CAM · PASCAL VOC 2007 valAverage Drop (%): 15.6 -> 13.2Improved
replace Score-CAM with Shap-CAMVGG16 CAM · PASCAL VOC 2007 valAverage Increase in Confidence (%): 28.9 -> 32.7Improved
replace Grad-CAM with Shap-CAMVGG16 CAM · ImageNet valAverage Drop (%): 47.8 -> 28.0Improved
replace Score-CAM with Shap-CAMVGG-16 · energy-based pointing gameproportion (%): 40.10 -> 40.45Improved
replace Score-CAM with Shap-CAMResNet18 · energy-based pointing gameproportion (%): 40.76 -> 41.28Improved
add Shap-CAM explanation loss to student training (without KD loss)WRN-16-2 student · CIFAR-10test error rate (%): 6.78 -> 6.69Improved
add Shap-CAM explanation loss to student training (with KD loss)WRN-16-2 student · CIFAR-10test error rate (%): 5.68 -> 5.37Improved
add Grad-CAM explanation loss to student training (without KD loss)WRN-16-2 student · CIFAR-10test error rate (%): 6.78 -> 6.86Hurt
add Grad-CAM explanation loss to student training (with KD loss)WRN-16-2 student · CIFAR-10test error rate (%): 5.68 -> 5.80Hurt

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