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 11–20 of 111 papers

TitleStatusHype
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance—0
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives—0
Retrieval-enriched zero-shot image classification in low-resource domains—0
TaxaBind: A Unified Embedding Space for Ecological ApplicationsCode1
Multilingual Vision-Language Pre-training for the Remote Sensing DomainCode0
Altogether: Image Captioning via Re-aligning Alt-textCode0
Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text DescribabilityCode0
Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual KnowledgeCode1
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features—0
LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model—0
Show:102550
← PrevPage 2 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