Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
lorebianchi98
/
Talk2DINOv3-ViTL
like
0
Image Segmentation
Safetensors
Pytorch
talk2dino
model_hub_mixin
pytorch_model_hub_mixin
DINOv3
CLIP
open-vocabulary segmentation
custom_code
arxiv:
2411.19331
License:
dinov3-license
Model card
Files
Files and versions
xet
Community
main
Talk2DINOv3-ViTL
/
assets
/
qualitatives
/
cityscapes
2.85 MB
1 contributor
History:
1 commit
lorebianchi98
First commit
29cb4d8
about 2 months ago
1_clipdinoiser.png
Safe
208 kB
xet
First commit
about 2 months ago
1_freeda.png
Safe
225 kB
xet
First commit
about 2 months ago
1_gt.png
Safe
215 kB
xet
First commit
about 2 months ago
1_image.png
Safe
732 kB
xet
First commit
about 2 months ago
1_proxyclip.png
Safe
225 kB
xet
First commit
about 2 months ago
1_talk2dino.png
Safe
223 kB
xet
First commit
about 2 months ago
1r_clipdinoiser.png
Safe
152 kB
xet
First commit
about 2 months ago
1r_freeda.png
Safe
168 kB
xet
First commit
about 2 months ago
1r_gt.png
Safe
160 kB
xet
First commit
about 2 months ago
1r_image.png
Safe
207 kB
xet
First commit
about 2 months ago
1r_proxyclip.png
Safe
166 kB
xet
First commit
about 2 months ago
1r_talk2dino.png
Safe
165 kB
xet
First commit
about 2 months ago