DINOv2 Giant is a high-capacity vision transformer trained via self-supervised learning, designed specifically for robus...
facebook
image-feature-extraction
52.4K
0
The ViT-Base-Patch16-224 (in21k) is a Vision Transformer pre-trained on the massive ImageNet-21k dataset. Unlike traditi...
google
image-feature-extraction
36.2K
3
DINOv2 Base is a self-supervised vision transformer designed for high-performance image feature extraction without requi...
facebook
image-feature-extraction
11.9K
3
The ViT-Base Patch14 DINOv2 model is a high-performance vision transformer trained via self-supervised learning on a cur...
timm
image-feature-extraction
10.0K
0
DINOv2-Small is a lightweight, self-supervised vision transformer designed for high-performance image feature extraction...
facebook
image-feature-extraction
7.0K
1
DINOv2 Large is a self-supervised vision transformer designed for high-performance image feature extraction without the ...
facebook
image-feature-extraction
4.8K
0
The ViT-Base Patch14 DINOv2 model is a high-performance vision transformer trained via self-supervised learning on a cur...
timm
image-feature-extraction
2.0K
0
The ViT-L/14 DINOv2 model is a high-capacity vision transformer trained via self-supervised learning on a massive, curat...
timm
image-feature-extraction
2.0K
0
The vit_small_patch14_reg4_dinov2 model is a lightweight vision transformer based on the DINOv2 architecture, optimized ...
timm
image-feature-extraction
2.0K
0
The ViT-Small Patch14 (DINOv2) is a lightweight vision transformer pre-trained on a massive, curated dataset of 142 mill...
timm
image-feature-extraction
1.9K
0
DINO ViT-B/16 is a self-supervised vision transformer designed for high-performance image feature extraction. Unlike tra...
facebook
image-feature-extraction
1.6K
0