AI Paper Atlas

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

BayesAdapter: Enhanced Uncertainty Estimation in CLIP Few-Shot Adaptation

Pablo Morales-Álvarez, Stergios Christodoulidis, Maria Vakalopoulou, Pablo Piantanida, José Dolz

IJCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 9 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
use Bayesian inference over the parameters instead of MAP point estimateCLAP · 11 datasets avg (ResNet50, all shots)ECE: 6.592 -> 4.151Improved
use Bayesian inference instead of MAPCLAP · 11 datasets avg (ViT-B/16, all shots)ECE: 5.351 -> 3.835Improved
use Bayesian inference instead of MAPCLAP · 11 datasets avg (ResNet50, all shots)coverage at 99% confidence: 7.103 -> 13.423Improved
use Bayesian inference instead of MAPCLAP · 11 datasets avg (ResNet50, all shots)Accuracy: 70.182 -> 69.476Hurt
use Bayesian inference instead of MAPCLAP · 11 datasets avg (ViT-B/16, all shots)Accuracy: 76.980 -> 76.420Hurt
increase to 32 shots per classBayesAdapter · 11 datasets (32 shots)AccuracyImproved
increase number of MC samples from 1 to 10 (ablation)BayesAdapter · 11 datasets avg (ablation, ResNet50)Accuracy: 69.443 -> 69.420No clear effect
increase prior std from 0.0001 to 0.01 (ablation)BayesAdapter · 11 datasets avg (ablation, ResNet50)Accuracy: 58.693 -> 69.437Improved
increase prior std from 0.01 to 1.0 (ablation)BayesAdapter · 11 datasets avg (ablation, ResNet50)Accuracy: 69.437 -> 68.747Hurt
increase prior std from 0.01 to 1.0 (ablation)BayesAdapter · 11 datasets avg (ablation, ResNet50)Cov@99% confidence: 9.213 -> 12.043Improved
add Bayesian variance parameters (training cost)CLAP · Caltech101 training time, 32 shotstraining time (s): 32.25 -> 42.40Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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