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 51–60 of 111 papers

TitleStatusHype
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models—0
Bayesian Test-Time Adaptation for Vision-Language Models—0
Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation—0
Bridge the Modality and Capability Gaps in Vision-Language Model Selection—0
CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization—0
CLAMP: Contrastive LAnguage Model Prompt-tuning—0
Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification—0
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance—0
CoAPT: Context Attribute words for Prompt Tuning—0
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features—0
Show:102550
← PrevPage 6 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