OpenCodePapers

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

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
PaperCodeAccuracy (Private)Accuracy (Public)ModelNameReleaseDate
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding✓ Link93.2MoE-ViE-H/142026-08-18
Perception Encoder: The best visual embeddings are not at the output of the network✓ Link92.6PE-Core G2025-04-17
CoCa: Contrastive Captioners are Image-Text Foundation Models✓ Link90.2CoCa2022-05-04
Scaling Vision Transformers to 22 Billion Parameters✓ Link90.1LiT-22B2023-02-10
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding✓ Link89.0MoE-ViE-L/162026-08-18
PaLI: A Jointly-Scaled Multilingual Language-Image Model✓ Link88.0LiT ViT-e2022-09-14
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters✓ Link87.3EVA-CLIP-18B2024-02-06
86.4BASIC (Lion)
Combined Scaling for Zero-shot Transfer Learning85.6BASIC2021-11-19
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks✓ Link83.8InternVL-C2023-12-21
EVA-CLIP: Improved Training Techniques for CLIP at Scale✓ Link82.1EVA-CLIP-E/14+2023-03-27
LiT: Zero-Shot Transfer with Locked-image text Tuning✓ Link79.4 37.8LiT-tuning2021-11-15
Demystifying CLIP Data✓ Link78.4MetaCLIP ViT-bigG/142023-09-28
Learning Transferable Visual Models From Natural Language Supervision✓ Link77.2CLIP2021-02-26
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision✓ Link75.8ALIGN2021-02-11
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities✓ Link69.5AltCLIP2022-11-12
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding✓ Link68.0MoE-ViE-B/162026-08-18
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training✓ Link58.7MobileCLIP-B2023-11-28
Multi-label Cluster Discrimination for Visual Representation Learning✓ Link56.4MLCD ViT-L/142024-07-24
PaLI: A Jointly-Scaled Multilingual Language-Image Model✓ Link44.7PaLI2022-09-14