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 81–90 of 111 papers

TitleStatusHype
Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification—0
Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models—0
PaLI: A Jointly-Scaled Multilingual Language-Image Model—0
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining—0
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training—0
Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation—0
Retrieval-enriched zero-shot image classification in low-resource domains—0
Segment Any Change—0
Semantic Compositions Enhance Vision-Language Contrastive Learning—0
Soundify: Matching Sound Effects to Video—0
Show:102550
← PrevPage 9 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