Image Segmentation
BiRefNet
Safetensors
background-removal
mask-generation
Dichotomous Image Segmentation
Camouflaged Object Detection
Salient Object Detection
pytorch_model_hub_mixin
model_hub_mixin
custom_code
Instructions to use ZhengPeng7/BiRefNet_HR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use ZhengPeng7/BiRefNet_HR with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("ZhengPeng7/BiRefNet_HR", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("ZhengPeng7/BiRefNet_HR") - Notebooks
- Google Colab
- Kaggle
Commit ·
fa76dd7
1
Parent(s): f69fb09
Add performance comparison table in README.
Browse files
README.md
CHANGED
|
@@ -14,6 +14,11 @@ license: mit
|
|
| 14 |
---
|
| 15 |
|
| 16 |
> This BiRefNet was trained with images in `2048x2048` for higher resolution inference.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
<h1 align="center">Bilateral Reference for High-Resolution Dichotomous Image Segmentation</h1>
|
| 19 |
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
> This BiRefNet was trained with images in `2048x2048` for higher resolution inference.
|
| 17 |
+
### Performance:
|
| 18 |
+
| Dataset | Method | maxFm | wFmeasure | MAE | Smeasure | meanEm | HCE | maxEm | meanFm | adpEm | adpFm | mBA | maxBIoU | meanBIoU |
|
| 19 |
+
| :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: | :------: |
|
| 20 |
+
| DIS-VD | BiRefNet_HR-general-epoch_130 | .925 | .894 | .026 | .927 | .952 | 811 | .960 | .909 | .944 | .888 | .828 | .837 | .817 |
|
| 21 |
+
| DIS-VD | BiRefNet-general-epoch_244 | .907 | .875 | .033 | .911 | .943 | 1069 | .953 | .892 | .944 | .879 | .000 | .000 | .000 |
|
| 22 |
|
| 23 |
<h1 align="center">Bilateral Reference for High-Resolution Dichotomous Image Segmentation</h1>
|
| 24 |
|