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 21–30 of 111 papers

TitleStatusHype
Can We Talk Models Into Seeing the World Differently?Code1
PerceptionCLIP: Visual Classification by Inferring and Conditioning on ContextsCode1
PromptStyler: Prompt-driven Style Generation for Source-free Domain GeneralizationCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language RepresentationsCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Structure Pretraining and Prompt Tuning for Knowledge Graph TransferCode1
CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsCode1
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse RetrievalCode1
Show:102550
← PrevPage 3 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