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
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet UpcyclingCode2
DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language ModelsCode0
Do Vision-Language Foundational models show Robust Visual Perception?Code0
CoAPT: Context Attribute words for Prompt Tuning—0
Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP InversionCode0
Semantic Compositions Enhance Vision-Language Contrastive Learning—0
PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent CollaborationCode2
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIPCode2
WATT: Weight Average Test-Time Adaptation of CLIPCode2
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models—0
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