Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
-
---
|
2 |
-
license: cc
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- self-supervised
|
7 |
+
- diffusion models
|
8 |
+
- mocov3
|
9 |
+
- simclrv2
|
10 |
+
- dino
|
11 |
+
- x-rays
|
12 |
+
- landmark detection
|
13 |
+
---
|
14 |
+
|
15 |
+
|
16 |
+
# Official PyTorch pre-trained models of the paper: "Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images" (WACV 2025)
|
17 |
+
|
18 |
+
|
19 |
+
The models available include:
|
20 |
+
|
21 |
+
- Our DDPM pre-trained model at 6k, 8k, 8k iterations respectively for the Chest, Cephalometric and Hand dataset
|
22 |
+
- MocoV3 densenet161 model at 10k iterations for the Chest, Cephalometric and Hand dataset
|
23 |
+
- SimClrV2 densenet161 model at 10k iterations for the Chest, Cephalometric and Hand dataset
|
24 |
+
- Dino densenet161 model at 10k iterations for the Chest, Cephalometric and Hand dataset
|
25 |
+
|
26 |
+
|
27 |
+
# Citation
|
28 |
+
|
29 |
+
Accepted at WACV (Winter Conference on Applications of Computer Vision) 2025.
|
30 |
+
|
31 |
+
### Bibtex
|
32 |
+
|
33 |
+
```
|
34 |
+
@article{DiVia2024,
|
35 |
+
author = {Di Via, R. and Odone, F. and Pastore, V. P.},
|
36 |
+
title = {Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images},
|
37 |
+
year = {2024},
|
38 |
+
journal = {arXiv},
|
39 |
+
volume = {2407.18125},
|
40 |
+
url = {https://arxiv.org/abs/2407.18125},
|
41 |
+
note = {Submitted on 25 Jul 2024 (v1), last revised 29 Oct 2024 (this version, v2)}
|
42 |
+
}
|
43 |
+
```
|
44 |
+
|
45 |
+
### APA
|
46 |
+
|
47 |
+
```
|
48 |
+
Di Via, R., Odone, F., & Pastore, V. P. (2024). Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images. ArXiv. https://arxiv.org/abs/2407.18125
|
49 |
+
```
|