Update README.md

README.md

@@ -5,17 +5,17 @@ metrics:
 - accuracy
 base_model:
 - microsoft/resnet-50
-pipeline_tag: image-classification
+pipeline_tag: image-classification, object-detection
 ---
 
-# Multi-Task Image Classifier
+# DualSight: A Multi-Task Image Classifier for Object Recognition and Authenticity Verification
 
 ## Model Overview
 This model is a **Multi-Task Image Classifier** that performs two tasks simultaneously:
-1. **Object Recognition:** Identifies the primary object in an image (e.g., "cat," "dog," "car," etc.).
+1. **Object Recognition:** Identifies the primary objects in an image (e.g., "cat," "dog," "car," etc.) using pseudo-labels generated through a YOLO-based object detection approach.
 2. **Authenticity Classification:** Determines whether the image is AI-generated or a real photograph.
 
-The model uses a **ResNet-50** backbone with two heads: one for multi-class object recognition (trained on pseudo-labels generated by a Vision Transformer) and another for binary classification (AI-generated vs. Real). It was trained on a subset of the [Hemg/AI-Generated-vs-Real-Images-Datasets](https://huggingface.co/datasets/Hemg/AI-Generated-vs-Real-Images-Datasets).
+The model uses a **ResNet-50** backbone with two heads: one for multi-class object recognition and another for binary classification (AI-generated vs. Real). It was trained on a subset of the [Hemg/AI-Generated-vs-Real-Images-Datasets](https://huggingface.co/datasets/Hemg/AI-Generated-vs-Real-Images-Datasets) and leverages YOLO for improved pseudo-labeling across the entire dataset.
 
 ## Intended Use
 This model is designed for:
@@ -32,12 +32,13 @@ from model import MultiTaskModel  # Your model definition
 # Instantiate your model architecture (must match training)
 model = MultiTaskModel(...)
 
+
 # Load the saved state dictionary (trained weights)
-model.load_state_dict(torch.load("multitask_model_weights.pth", map_location="cpu"))
+model.load_state_dict(torch.load("Yolloplusclassproject_weights.pth", map_location="cpu"))
 model.eval()
 ```
 Alternatively, you can test the model directly via our interactive demo:
-[Test the Model Here](https://huggingface.co/spaces/Abdu07/multitask-demo)
+[Test the Model Here(CLICK)](https://huggingface.co/spaces/Abdu07/DualSight-Demo)  
 
 ## Training Data and Evaluation
 - **Dataset:** The model was trained on a subset of the [Hemg/AI-Generated-vs-Real-Images-Datasets](https://huggingface.co/datasets/Hemg/AI-Generated-vs-Real-Images-Datasets) comprising approximately 152k images.