Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
lorebianchi98
/
Talk2DINO-ViTB
like
2
Image Segmentation
Safetensors
Pytorch
talk2dino
model_hub_mixin
pytorch_model_hub_mixin
DINOv2
CLIP
open-vocabulary segmentation
custom_code
arxiv:
2411.19331
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
Talk2DINO-ViTB
/
assets
/
qualitatives
/
cityscapes
2.85 MB
2 contributors
History:
1 commit
lorebianchi98
Added assets
301a7ac
verified
4 months ago
1_clipdinoiser.png
208 kB
xet
Added assets
4 months ago
1_freeda.png
225 kB
xet
Added assets
4 months ago
1_gt.png
215 kB
xet
Added assets
4 months ago
1_image.png
732 kB
xet
Added assets
4 months ago
1_proxyclip.png
225 kB
xet
Added assets
4 months ago
1_talk2dino.png
223 kB
xet
Added assets
4 months ago
1r_clipdinoiser.png
152 kB
xet
Added assets
4 months ago
1r_freeda.png
168 kB
xet
Added assets
4 months ago
1r_gt.png
160 kB
xet
Added assets
4 months ago
1r_image.png
207 kB
xet
Added assets
4 months ago
1r_proxyclip.png
166 kB
xet
Added assets
4 months ago
1r_talk2dino.png
165 kB
xet
Added assets
4 months ago
