Transformers for Computer Vision

English Channel Video titled: "Object detection Using Detection Transformer (Detr) on custom dataset" 📌 **What You’ll Learn:** ✅ Step-by-step implementation of **DETR on a custom dataset** ✅ How CNN features are fed into a **Transformer encoder-decoder architecture** ✅ Understanding **self-attention, cross-attention, and positional encoding** ✅ Using **bipartite graph matching** for ground truth assignment ✅ Practical example using a **bone fracture dataset** from Roboflow 🔗 **Dataset Used:** https://universe.roboflow.com/roboflow-100/bone-fracture-7fylg

English Channel Video titled : "Image Classification Using Swin Transformer" 📌 **What You’ll Learn:** ✅ Step-by-step implementation of a **custom Swin Transformer model** ✅ How Swin Transformers combine **global attention with local feature extraction** ✅ Understanding **shifted windows** for efficient image processing ✅ How to handle **large-scale image datasets** ✅ Applications in **image classification, object detection, and segmentation**

English Channel Video titled: "Vision Transformer for Image Classification Using transfer learning" 📌 **What You’ll Learn:** ✅ Step-by-step **implementation of ViT using transfer learning** ✅ How Vision Transformers apply **Transformer architecture from NLP to computer vision** ✅ Understanding **patch embeddings, positional encoding, and self-attention** ✅ How ViT compares with conventional CNNs on image classification tasks ✅ Tips for using **transfer learning** to improve model performance

English Channel Video titled : "Image Classification Using Vision Transformer | ViTs" In this tutorial, we explore how **Vision Transformers**, introduced by the Google Brain team in 2020, can achieve **competitive performance on image classification tasks**, often rivaling traditional CNNs. 📌 **What You’ll Learn:** ✅ How Vision Transformers apply **Transformer architecture from NLP to computer vision** ✅ Step-by-step **implementation for image classification** ✅ Understanding **patch embeddings, positional encoding, and self-attention** ✅ How ViT compares with traditional CNNs on benchmark datasets

📌 **What You’ll Learn:** ✅ Setting up a **Google Colab environment** for ViT training ✅ Preparing and loading your **custom image dataset** ✅ Training a **Vision Transformer (ViT) model** step by step ✅ Evaluating model performance and metrics ✅ Tips for improving accuracy and efficiency