Chapter 9: CNNs & Computer Vision
Chapter Overview
CNN building blocks · Architecture evolution · Transfer learning · Detection & segmentation · Vision-language models · Generative vision
Sections
1
CNN Building Blocks
Convolution · Pooling · Feature hierarchies
2
Architecture Evolution
LeNet → ResNet → ViT
3
Transfer Learning
The practical skill
4
Image Augmentation
Geometric · Color · CutMix · MixUp
5
Detection & Segmentation
6
Modern Vision
CLIP · Stable Diffusion · Multimodal LLMs
7
Interpretability & Visualization
Grad-CAM · Saliency · Debugging
8
Nice to Know
Video · Pose · Visual search · NeRF