OpenCodePapers

zero-shot-transfer-image-classification-on-imagenet-r

Image ClassificationZero-Shot Image ClassificationZero-Shot Transfer Image Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
96.8BASIC (Lion)
CoCa: Contrastive Captioners are Image-Text Foundation Models✓ Link96.5CoCa2022-05-04
Perception Encoder: The best visual embeddings are not at the output of the network✓ Link96.5PE-Core G2025-04-17
PaLI: A Jointly-Scaled Multilingual Language-Image Model✓ Link96.1LiT ViT-e2022-09-14
Scaling Vision Transformers to 22 Billion Parameters✓ Link96.0LiT-22B2023-02-10
Combined Scaling for Zero-shot Transfer Learning95.7BASIC2021-11-19
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters✓ Link95.7EVA-CLIP-18B2024-02-06
EVA-CLIP: Improved Training Techniques for CLIP at Scale✓ Link94.5EVA-CLIP-E/14+2023-03-27
Demystifying CLIP Data✓ Link94.1MetaCLIP ViT-bigG/142023-09-28
LiT: Zero-Shot Transfer with Locked-image text Tuning✓ Link93.9LiT-tuning2021-11-15
Conformal Prediction for Zero-Shot Models✓ Link93.4Conf-OT (MetaCLIP ViT-H/14)2025-05-30
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision✓ Link92.2ALIGN2021-02-11
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training✓ Link89.6MobileCLIP-B2023-11-28
Learning Transferable Visual Models From Natural Language Supervision✓ Link88.9CLIP2021-02-26
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities✓ Link87.2AltCLIP2022-11-12
Multi-label Cluster Discrimination for Visual Representation Learning✓ Link85.1MLCD ViT-L/142024-07-24
PaLI: A Jointly-Scaled Multilingual Language-Image Model✓ Link81.97PaLI2022-09-14
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training40CLIP ViT-B/16 (LAION-BVD, zero-shot)2026-08-25