AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, Sarah Monazam Erfani

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 0 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
apply DAT density-aware translationCLIP ViT-B/32 · Waterbirdsworst-group accuracy: 41.37 -> 75.08Improved
apply DAT density-aware translationCLIP ViT-L/14 · Waterbirdsworst-group accuracy: 31.93 -> 83.33Improved
apply DAT density-aware translationCLIP ResNet50 · Waterbirdsworst-group accuracy: 35.36 -> 75.08Improved
apply DAT density-aware translationCLIP ViT-B/32 · CelebAworst-group accuracy: 78.89 -> 78.53No clear effect
apply DAT density-aware translationCLIP ViT-L/14 · CelebAworst-group accuracy: 73.35 -> 84.94Improved
apply DAT density-aware translationBiomedCLIP · COVID-19worst-group accuracy: 44.83 -> 65.22Improved
apply DAT density-aware translationCLIP ViT-L/14 · FMoWworst-group accuracy: 18.06 -> 27.75Improved
apply DAT density-aware translationALIGN · Waterbirdsworst-group accuracy: 50.3 -> 73.36Improved
apply DAT density-aware translationAltCLIP · Waterbirdsworst-group accuracy: 35.8 -> 81.31Improved
use SLOF density instead of DAO (MLE, k=30) (ablation)DAT · Waterbirds ViT-B/32worst-group accuracy: 71.88 -> 75.08Improved
use SLOF density instead of k-NN distance (k=10) (ablation)DAT · Waterbirds ViT-B/32worst-group accuracy: 71.49 -> 75.08Improved
use DAT instead of TIE for computeCLIP ViT-B/32 · CelebAcomputation time (s): 970 -> 203Improved

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