SOTAVerified

Zero-Shot Image Classification

Zero-shot image classification is a technique in computer vision where a model can classify images into categories that were not present during training. This is achieved by leveraging semantic information about the categories, such as textual descriptions or relationships between classes.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 111 papers

TitleStatusHype
LiT: Zero-Shot Transfer with Locked-image text TuningCode1
FILIP: Fine-grained Interactive Language-Image Pre-TrainingCode1
Benchmarking Knowledge-driven Zero-shot LearningCode1
Open-vocabulary Object Detection via Vision and Language Knowledge DistillationCode1
Generative Multi-Label Zero-Shot LearningCode1
CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization—0
Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation—0
Bayesian Test-Time Adaptation for Vision-Language Models—0
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification—0
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations—0
Show:102550
← PrevPage 5 of 12Next →
All datasetsCountry211ICinWODinW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OpenClip H/14 (34B)(Laion2B)Top-1 accuracy30.01—Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP (ViT B-32)Average Score56.64—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIP (Tiny A)Average Score11.4—Unverified