OpenCodePapers

zero-shot-transfer-image-classification-on-4

Zero-Shot Transfer Image Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
[]()96.8BASIC (Lion)
CoCa: Contrastive Captioners are Image-Text Foundation Models✓ Link96.5CoCa2022-05-04
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
LiT: Zero-Shot Transfer with Locked-image text Tuning✓ Link93.9LiT-tuning2021-11-15
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision✓ Link92.2ALIGN2021-02-11
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
PaLI: A Jointly-Scaled Multilingual Language-Image Model✓ Link81.97PaLI2022-09-14
Check out how to contribute new results.