Vision backbones Collection of SOTA backbones (features extraction, image classification, multimodal, ...) google/vit-base-patch16-224-in21k Image Feature Extraction • 86.4M • Updated Feb 5, 2024 • 791k • 416 facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 686k • 544 facebook/dinov2-large Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 799k • 117 microsoft/swin-base-patch4-window7-224 Image Classification • 87.8M • Updated Sep 10, 2023 • 44k • • 27
google/vit-base-patch16-224-in21k Image Feature Extraction • 86.4M • Updated Feb 5, 2024 • 791k • 416
facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 686k • 544
microsoft/swin-base-patch4-window7-224 Image Classification • 87.8M • Updated Sep 10, 2023 • 44k • • 27
Vision backbones Collection of SOTA backbones (features extraction, image classification, multimodal, ...) google/vit-base-patch16-224-in21k Image Feature Extraction • 86.4M • Updated Feb 5, 2024 • 791k • 416 facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 686k • 544 facebook/dinov2-large Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 799k • 117 microsoft/swin-base-patch4-window7-224 Image Classification • 87.8M • Updated Sep 10, 2023 • 44k • • 27
google/vit-base-patch16-224-in21k Image Feature Extraction • 86.4M • Updated Feb 5, 2024 • 791k • 416
facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 686k • 544
microsoft/swin-base-patch4-window7-224 Image Classification • 87.8M • Updated Sep 10, 2023 • 44k • • 27