AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Towards Better Explanations of Class Activation Mapping

Hyungsik Jung, Youngrock Oh

ICCV 2021 · Architectures and efficiency › CNN design · approach: Biologically inspired CNN explanation · 124 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
increase number of orderings from 1 to 100 (ablation)SHAP-CAM · ImageNetIncrease in Confidence (%): 25.9 -> 26.4Improved
increase number of orderings from 1 to 100 (ablation)SHAP-CAM · VOCIncrease in Confidence (%): 37.4 -> 43.6Improved
increase number of orderings from 1 to 100 (ablation)SHAP-CAM · COCOAverage Drop (%): 23.98 -> 18.27Improved
increase number of orderings from 1 to 100 (ablation)SHAP-CAM · ImageNetAverage Drop in Deletion (%): 32.64 -> 33.03Improved
use SHAP-based coefficients (LIFT-CAM) instead of Grad-CAMVGG16 CAM · VOCIncrease in Confidence (%): 32.7 -> 38.7Improved
use LIFT-CAM instead of Ablation-CAM coefficientsVGG16 CAM · COCOIncrease in Confidence (%): 35.0 -> 39.3Improved
use LIFT-CAM instead of Ablation-CAM coefficientsVGG16 CAM · COCOAverage Drop in Deletion (%): 26.75 -> 26.34Hurt
use LIFT-CAM instead of Ablation-CAM coefficientsVGG16 CAM · ImageNetcosine similarity to SHAP values: 0.972 -> 0.980Improved
use LIFT-CAM instead of Ablation-CAM coefficientsVGG16 CAM · ImageNetInsertion AUC: 0.4685 -> 0.4712Improved
use LIFT-CAM instead of Ablation-CAM coefficientsVGG16 CAM · ImageNetenergy in bounding box (%): 51.87 -> 52.43Improved
use LIFT-CAM instead of Grad-CAMbasic VQA · VQA v2.0Average Drop (%): 16.71 -> 14.14Improved
use LIFT-CAM instead of Grad-CAMbasic VQA · VQA v2.0Increase in Confidence (%): 41.95 -> 43.39Improved

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