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 76–100 of 111 papers

TitleStatusHype
Image-Caption Encoding for Improving Zero-Shot GeneralizationCode0
Segment Any Change—0
CLAMP: Contrastive LAnguage Model Prompt-tuning—0
LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models—0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Efficient Model-Agnostic Multi-Group Equivariant Networks—0
Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models—0
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training—0
Semantically-Prompted Language Models Improve Visual Descriptions—0
Learning from Children: Improving Image-Caption Pretraining via CurriculumCode0
Text-to-Image Diffusion Models are Zero-Shot ClassifiersCode0
Language-Driven Anchors for Zero-Shot Adversarial RobustnessCode0
Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities—0
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training—0
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning—0
When are Lemons Purple? The Concept Association Bias of Vision-Language Models—0
CLIPPO: Image-and-Language Understanding from Pixels Only—0
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification—0
Generative Negative Text Replay for Continual Vision-Language Pretraining—0
Text2Model: Text-based Model Induction for Zero-shot Image Classification—0
Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss—0
I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification—0
PaLI: A Jointly-Scaled Multilingual Language-Image Model—0
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining—0
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
Show:102550
← PrevPage 4 of 5Next →
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