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 71–80 of 111 papers

TitleStatusHype
When are Lemons Purple? The Concept Association Bias of Vision-Language Models—0
CLIPPO: Image-and-Language Understanding from Pixels OnlyCode0
Reproducible scaling laws for contrastive language-image learningCode1
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification—0
AltCLIP: Altering the Language Encoder in CLIP for Extended Language CapabilitiesCode4
Chinese CLIP: Contrastive Vision-Language Pretraining in ChineseCode5
Generative Negative Text Replay for Continual Vision-Language Pretraining—0
Text2Model: Text-based Model Induction for Zero-shot Image Classification—0
General Image Descriptors for Open World Image Retrieval using ViT CLIPCode1
Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss—0
Show:102550
← PrevPage 8 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