AI Paper Atlas

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

Linking in Style: Understanding learned features in deep learning models

Maren Wehrheim, Pamela Osuna Vargas, Matthias Kaschube

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 1 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
link ResNet-50 penultimate layer to StyleGAN-XL W-space with a linear regression linking networkLinking network · ImageNet classes, ResNet-50 and StyleGAN-XLMSE between w and cycled w, MoCov2 image distanceImproved
cluster W-space versus representation space by class with k-meansStyleGAN-XL W-space and ResNet-50 representation space · five random ImageNet classes, 100 repetitionsAdjusted Rand IndexNo clear effect
use counterfactual quantification pipeline instead of MSE or LPIPS along the trajectoryDecision-boundary analysis · Counterfactual trajectories between dog classesinterpretability of feature changesImproved
apply the linking approach to a ViT classifier instead of a CNNLinking network · ViT classifiersapplicabilityHurt
train linking network on a classifier and GAN trained on similar but different datasetsLinking network · face datasetsability to reveal relevant featuresNo clear effect

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