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 101–111 of 111 papers

TitleStatusHype
Open-vocabulary Object Detection via Vision and Language Knowledge DistillationCode1
Large-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions—0
Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification—0
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionCode2
Generative Multi-Label Zero-Shot LearningCode1
Visual-Semantic Embedding Model Informed by Structured Knowledge—0
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions—0
Zero-Shot Image Classification Using Coupled Dictionary Embedding—0
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification—0
Gaze Embeddings for Zero-Shot Image Classification—0
Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification—0
Show:102550
← PrevPage 5 of 5Next →
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