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
FILIP: Fine-grained Interactive Language-Image Pre-TrainingCode1
General Image Descriptors for Open World Image Retrieval using ViT CLIPCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
Benchmarking Knowledge-driven Zero-shot LearningCode1
LiT: Zero-Shot Transfer with Locked-image text TuningCode1
Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image ClassificationCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsCode1
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via NegationsCode1
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