AI Paper Atlas

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

Bayesian Prompt Learning for Image-Language Model Generalization

Mohammad Mahdi Derakhshani, Enrique Sanchez, Adrian Bulat, Victor G. Turrisi da Costa, Cees G.M. Snoek, Georgios Tzimiropoulos, Brais Martinez

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 74 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
model prompts variationally (conditional Bayesian prompt learning) instead of CoCoOpCLIP ViT-B/16 prompt learning · Task I: unseen classes (11 datasets, avg)accuracy (%): 71.69 -> 74.94Improved
use prompt-space distribution instead of ProDACLIP ViT-B/16 prompt learning · Task I: unseen classes (11 datasets, avg)accuracy (%): 72.30 -> 74.94Improved
use Bayesian prompt learning instead of CoCoOp for cross-dataset transferCLIP ViT-B/16 prompt learning · Task II: cross-dataset (ImageNet to 10 datasets, avg)accuracy (%): 65.59 -> 65.95Improved
use Bayesian prompt learning instead of CoCoOp for cross-domain robustnessCLIP ViT-B/16 prompt learning · Task III: cross-domain (ImageNet variants, avg)accuracy (%): 59.88 -> 60.44Improved
use Bayesian prompt learning instead of CoOp for in-domain accuracyCLIP ViT-B/16 prompt learning · In-domain performance, Task I averageaccuracy (%): 82.66 -> 80.10Hurt
add variational formulation (unconditional) over CoOp baseline (ablation)CoOp · Task I: DTD unseenaccuracy (%): 41.18 -> 58.70Improved
add image conditioning to the latent distribution (ablation)Bayesian prompt learning · Task I: unseen classes (5 datasets)accuracy (%): Flowers102 75.90 -> 70.40; DTD 58.70 -> 60.80Mixed
use learned posterior N(mu(x), Sigma(x)) instead of N(0,I) sample (ablation)Bayesian prompt learning · Task I: DTD unseen (one seed)accuracy (%): 26.60 -> 56.40Improved
increase Monte Carlo samples from 1 to 20 at inference (ablation)Bayesian prompt learning · Task I: EuroSAT unseenaccuracy (%): 64.50 -> 74.80Improved
increase Monte Carlo samples beyond 20 (ablation)Bayesian prompt learning · Task I: unseen classes (5 datasets)accuracy (%): EuroSAT 74.80 -> 76.20 at 80 samples; FGVC 35.00 -> 34.70No clear effect
initialize context tokens with 'An image of a {class}' instead of random (ablation)Bayesian prompt learning · Task I: EuroSAT unseen (one seed)accuracy (%): 75.10 -> 77.90Improved
use variational sampling instead of naive prompt ensemble on CoCoOp (ablation)CoCoOp · Task I: unseen classes (5 datasets)accuracy (%): EuroSAT 66.10 -> 75.30; DTD 52.17 -> 60.80Improved

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