Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,8 @@ by Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuse
|
|
| 17 |
> **Key Insight**: Given sufficient scale and pretraining, a plain ViT along with additional few params can perform segmentation without the need for task-specific decoders or pixel fusion modules. The same model backbone supports semantic, instance, and panoptic segmentation with different post-processing 🤗
|
| 18 |
|
| 19 |
The original implementation can be found in this [repository](https://github.com/tue-mps/eomt).
|
| 20 |
-
|
|
|
|
| 21 |
|
| 22 |
---
|
| 23 |
|
|
|
|
| 17 |
> **Key Insight**: Given sufficient scale and pretraining, a plain ViT along with additional few params can perform segmentation without the need for task-specific decoders or pixel fusion modules. The same model backbone supports semantic, instance, and panoptic segmentation with different post-processing 🤗
|
| 18 |
|
| 19 |
The original implementation can be found in this [repository](https://github.com/tue-mps/eomt).
|
| 20 |
+
|
| 21 |
+
The HuggingFace model page is available at this [link](https://huggingface.co/papers/2503.19108).
|
| 22 |
|
| 23 |
---
|
| 24 |
|