prakashchhipa
/

MPD_SSL

Image Classification

Perspective Distortion

Self-supervised Learning

Model card Files Files and versions Community

prakashchhipa commited on Jul 16

Commit

ddb810c

•

1 Parent(s): 8fe897f

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -20,10 +20,10 @@ Publication- *Möbius Transform for Mitigating Perspective Distortions in Repres
 **Model Description**
-This release includes two self-supervised pretrained models integrated with the Mitigating Perspective Distortion (MPD) technique. The models are:
-1. ResNet50 pretrained using SimCLR (Simple Framework for Contrastive Learning of Visual Representations)
-2. ViT-small pretrained using DINO (Self-Distillation with No Labels)
 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.

 **Model Description**
+This release includes two self-supervised pretrained models integrated with the Mitigating Perspective Distortion (MPD) method. The models are:
+1. ResNet50 pretrained using SimCLR- https://huggingface.co/prakashchhipa/MPD_SSL/blob/main/SimCLR_resnet50_with_MPD.pth.tar
+2. ViT-small pretrained using DINO- https://huggingface.co/prakashchhipa/MPD_SSL/blob/main/DINO_vit-small_with_MPD.pth
 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.