Update README.md
Browse files
README.md
CHANGED
|
@@ -20,10 +20,10 @@ Publication- *Möbius Transform for Mitigating Perspective Distortions in Repres
|
|
| 20 |
|
| 21 |
**Model Description**
|
| 22 |
|
| 23 |
-
This release includes two self-supervised pretrained models integrated with the Mitigating Perspective Distortion (MPD)
|
| 24 |
|
| 25 |
-
1. ResNet50 pretrained using SimCLR
|
| 26 |
-
2. ViT-small pretrained using DINO
|
| 27 |
|
| 28 |
Both models were trained with a *batch size of 512* over *100 epochs*. The MPD method enhances the robustness of these models by simulating real-world perspective distortions, making them more robust in various computer vision tasks.
|
| 29 |
|
|
|
|
| 20 |
|
| 21 |
**Model Description**
|
| 22 |
|
| 23 |
+
This release includes two self-supervised pretrained models integrated with the Mitigating Perspective Distortion (MPD) method. The models are:
|
| 24 |
|
| 25 |
+
1. ResNet50 pretrained using SimCLR- https://huggingface.co/prakashchhipa/MPD_SSL/blob/main/SimCLR_resnet50_with_MPD.pth.tar
|
| 26 |
+
2. ViT-small pretrained using DINO- https://huggingface.co/prakashchhipa/MPD_SSL/blob/main/DINO_vit-small_with_MPD.pth
|
| 27 |
|
| 28 |
Both models were trained with a *batch size of 512* over *100 epochs*. The MPD method enhances the robustness of these models by simulating real-world perspective distortions, making them more robust in various computer vision tasks.
|
| 29 |
|