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 61–70 of 111 papers

TitleStatusHype
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning—0
Efficient Model-Agnostic Multi-Group Equivariant Networks—0
Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss—0
Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning—0
Gaze Embeddings for Zero-Shot Image Classification—0
Generative Negative Text Replay for Continual Vision-Language Pretraining—0
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training—0
I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification—0
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification—0
CLIPPO: Image-and-Language Understanding from Pixels Only—0
Show:102550
← PrevPage 7 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