Link model card to paper
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,7 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- computer-vision
|
| 7 |
- self-supervised-learning
|
|
@@ -11,16 +15,14 @@ tags:
|
|
| 11 |
- depth-estimation
|
| 12 |
- semantic-segmentation
|
| 13 |
- pytorch
|
| 14 |
-
datasets:
|
| 15 |
-
- custom
|
| 16 |
-
library_name: pytorch
|
| 17 |
-
pipeline_tag: image-feature-extraction
|
| 18 |
---
|
| 19 |
|
| 20 |
# LingBot-Vision
|
| 21 |
|
| 22 |
**LingBot-Vision** is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
This Hugging Face repository stores a backbone-only PyTorch checkpoint as `model.pt`. It is intended for inference, feature extraction, PCA visualization, and downstream dense prediction research.
|
| 25 |
|
| 26 |
## Model Details
|
|
@@ -136,4 +138,4 @@ The `variant` argument can be `giant`, `large`, `base`, or `small`. You can also
|
|
| 136 |
## Model Card Contact
|
| 137 |
|
| 138 |
- **Issues:** https://github.com/robbyant/lingbot-vision/issues
|
| 139 |
-
- **Email:** fuzelin.fzl@antgroup.com, xuenan.xue@antgroup.com
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets:
|
| 3 |
+
- custom
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
library_name: pytorch
|
| 7 |
+
license: apache-2.0
|
| 8 |
+
pipeline_tag: image-feature-extraction
|
| 9 |
tags:
|
| 10 |
- computer-vision
|
| 11 |
- self-supervised-learning
|
|
|
|
| 15 |
- depth-estimation
|
| 16 |
- semantic-segmentation
|
| 17 |
- pytorch
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
# LingBot-Vision
|
| 21 |
|
| 22 |
**LingBot-Vision** is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
|
| 23 |
|
| 24 |
+
This model was introduced in the paper [Vision Pretraining for Dense Spatial Perception](https://huggingface.co/papers/2607.05247).
|
| 25 |
+
|
| 26 |
This Hugging Face repository stores a backbone-only PyTorch checkpoint as `model.pt`. It is intended for inference, feature extraction, PCA visualization, and downstream dense prediction research.
|
| 27 |
|
| 28 |
## Model Details
|
|
|
|
| 138 |
## Model Card Contact
|
| 139 |
|
| 140 |
- **Issues:** https://github.com/robbyant/lingbot-vision/issues
|
| 141 |
+
- **Email:** fuzelin.fzl@antgroup.com, xuenan.xue@antgroup.com
|