Update readme with ISDNET pytorch implementation link

README.md

@@ -318,6 +318,7 @@ python main.py eval  --config configs/config_CRAG_aug.yaml --checkpoint weights/
 | Swin-B + UPerNet (retrained)            | 64.02 | 76.64 | 32.57 | – | – |
 | Swin-L + UPerNet                        | 63.36 | 76.35 | – | 420 | 27.8 |
 | *Dual-branch baselines*                 |            |           |             |          |       |
+| ISDNet (trained with [Pytorch implementation](https://huggingface.co/heig-vd-geo/ISDNet-pytorch)) |52.77|-|-|-|
 | Dual Swin-Base (late fusion, no CA)     | 64.25 | – | – | 398 | 19.4 |
 | **CASWiT-Base + UPerNet**                  |  65.11     |  77.71    |    35.87    |489 | 15.4 |
 | **CASWiT-Base-SSL + UPerNet**              |  65.35     |  77.87    |    35.99    |489 | 15.4 |
@@ -427,4 +428,4 @@ This project is licensed under the MIT License - see the LICENSE file for detail
 - [CRAG](https://github.com/XiaoyuZHK/CRAG-Dataset_Aug_ToCOCO) for the dataset
 - [ISIC](https://challenge.isic-archive.com/) for the dataset
 
----
+---