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
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionCode2
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense PredictionCode2
What does a platypus look like? Generating customized prompts for zero-shot image classificationCode2
CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image ClassificationCode1
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot LearningCode1
General Image Descriptors for Open World Image Retrieval using ViT CLIPCode1
Generative Multi-Label Zero-Shot LearningCode1
Disentangled Ontology Embedding for Zero-shot LearningCode1
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