AI Paper Atlas

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

Better Understanding Differences in Attribution Methods via Systematic Evaluations

Sukrut Rao, Moritz Böhle, Bernt Schiele

TPAMI 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 6 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 Gaussian smoothing to IntGrad attributions at the input layerIntGrad · GridPG ImageNet VGG19Spearman correlation with Grad-CAM final layer: 0.34 -> 0.80Improved
add Gaussian smoothing to IxG with large kernelsIxG · GridPG Resnet152localization / correlationNo clear effect
use Gaussian smoothing instead of SmoothGrad noise averagingIntGrad and IxG · GridPG ImageNet VGG11 / Resnet18localization scoreImproved
add Gaussian smoothing to IntGrad and IxGIntGrad and IxG · DiFull ImageNetlocalization scoreHurt
apply LRP z+ rule to functionally equivalent transformed modelLRP z+ · DiFull VGG19attribution to disconnected regionsHurt

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