AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions

Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 3 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
evaluate CBMs on novel single-attribute substitutions (SUB) instead of CUB test classesConcept Bottleneck Models · SUB vs CUBconcept accuracy (%): 96.7 (CUB test) -> 40.8 (SUB S+), independent CBMHurt
use Concept Embedding Model instead of standard CBMConcept Bottleneck Models · SUB (S+ accuracy)S+ accuracy (%): 40.8 -> 45.7Improved
use soft concept labels instead of hard labels (ablation)CBM (independent) · SUB (S+ accuracy)S+ accuracy (%): 40.8 -> 12.9Hurt
use per-image concept labels instead of class-level attribute vectors (ablation)CBM (independent) · SUB (S+ accuracy)S+ accuracy (%): 40.8 -> 32.8Hurt
train concepts individually (per-concept CBM) (ablation)CBM · SUB (S+ accuracy)S+ accuracy (%): 40.8 -> 0.39Hurt
train CBM jointly instead of independently (ablation)CBM · SUB (S+ accuracy)S+ accuracy (%): 40.8 -> 34.3Hurt
scale up to large pretrained VLM backbones (CLIP, SigLIP, EVA-CLIP)Concept recognition · SUB VLMs (S+ accuracy)S+ accuracy (%): 9.3 (random) -> 46.8 (EVA-CLIP) vs human 92.4Mixed
add Tied Diffusion Guidance to FLUX prompting for attribute substitution (ablation)FLUX.1-dev · SUB generationqualitative attribute fidelityImproved
use SUB human-validated labels instead of CUB image-level labelsBenchmark annotation · Label correctnessattribute label agreement (%): 57.50 -> 98.90Improved

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