AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Determining the Relevance of Features for Deep Neural Networks

Christian Reimers, Jakob Runge, Joachim Denzler

ECCV 2020 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 22 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
test relevance with causal conditional-independence test instead of r2pattern relevance · Synthetic box vs cross toy taskidentifying the used pattern: r2 0.985 for non-used pattern vs p-value 0.608 (r2 1.000, p-value 0.000 for kernel pattern)Improved
compare ML-GCN to SRN on area relevanceSRN · MS COCO val 2014 (80 classes)classes where area is relevant: 69 -> 73Improved
compare ML-GCN to SRN on vertical position relevance (lower is better)SRN · MS COCO val 2014 (80 classes)classes where vertical position is relevant: 54 -> 51Improved
compare ML-GCN to SRN on horizontal position relevance (lower is better)SRN · MS COCO val 2014 (80 classes)classes where horizontal position is relevant: 16 -> 10Improved
random horizontal flipping augmentation (horizontal vs vertical half)ML-GCN · MS COCO val 2014 (80 classes)classes where half is relevant: 1 class horizontal vs 25 classes verticalImproved
yellow lores area or color as featureLSFGC · CUB200 (White-crowned vs White-throated sparrow, 120 images)p-value: 0.406 and 0.446No clear effect
white throat markings area or color as featureLSFGC · CUB200 (White-crowned vs White-throated sparrow, 120 images)p-value: 0.404 and 0.330No clear effect
shape symmetry as feature: seborrheic keratosis vs melanomaSLA · HAM10000 / ISIC 2017 validationp-value: 0.632 -> 0.022Mixed

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