AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

STEEX: Steering Counterfactual Explanations with Semantics

Paul Jacob, Éloi Zablocki, Hédi Ben-Younes, Mickaël Chen, Patrick Pérez, Matthieu Cord

ECCV 2022 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 47 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 the distance loss L_dist (lambda=0.3 instead of 0) (ablation)STEEX · CelebAMask-HQ SmileFVA (%): 65.2 -> 97.6Improved
add the distance loss L_dist (lambda=0.3 instead of 0) (ablation)STEEX · CelebAMask-HQ YoungFVA (%): 37.0 -> 96.0Improved
add the distance loss L_dist (ablation)STEEX · CelebAMask-HQ SmileFID: 29.7 -> 21.9Improved
add the distance loss L_dist (ablation)STEEX · CelebAMask-HQ YoungFID: 45.7 -> 26.8Improved
use ground-truth instead of predicted segmentation masks (ablation)STEEX · CelebAMask-HQ SmileFID: 21.9 -> 21.2No clear effect
use ground-truth instead of predicted segmentation masks (ablation)STEEX · CelebAMask-HQ YoungFVA (%): 96.0 -> 98.2No clear effect
replace PE/DiVE with STEEX semantic-guided generationSTEEX · CelebAMask-HQ SmileFID: 52.4 -> 21.9 (vs PE), 107.0 -> 21.9 (vs DiVE)Improved
replace PE/DiVE with STEEX semantic-guided generationSTEEX · CelebAMask-HQ YoungFVA (%): 76.2 -> 96.0 (vs PE), 32.3 -> 96.0 (vs DiVE)Improved
replace PE/DiVE with STEEX semantic-guided generationSTEEX · CelebAMask-HQ YoungMNAC: 8.51 -> 5.63 (vs PE), 6.76 -> 5.63 (vs DiVE)Improved
replace DiVE with STEEX on low-res CelebASTEEX · CelebA SmileFVA (%): 97.3 (DiVE) vs 96.9 (STEEX)No clear effect
scale resolution from CelebA 128 to CelebAMask-HQ 256DiVE · CelebA Smile -> CelebAMask-HQ SmileFID: 29.4 -> 107.0Hurt

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