Book 7 — Computer Vision

From pixels to vision transformers.

Image Basics

• Pixels & RGB
• Convolution, filters, kernels
• Padding & stride
• Pooling

Architectures

• CNNs
• ResNet
• Transfer learning
• Object detection (YOLO, Faster R-CNN)
• Segmentation (U-Net)
• Vision Transformers
• Image embeddings & multimodal vision

Status

Complete deep-dive coverage of convolutional foundations, modern CNN architectures and transfer learning, and advanced vision tasks including U-Net, Vision Transformers, and CLIP.