Deep Learning Foundations for Vision

Chapter 10: Convolutional Neural Networks (CNNs): Fundamentals (Convolution, pooling, activation functions, backpropagation) Chapter 11: Types of Convolutions (Standard, dilated, transposed, depthwise separable, group, deformable) Chapter 12: Data Augmentation Techniques (Flipping, rotation, color jitter, CutMix, MixUp, synthetic augmentation) Chapter 13: Pretraining and Transfer Learning (ImageNet, fine-tuning, domain adaptation, frozen vs. unfrozen layers) Chapter 14: Training Techniques and Optimization (SGD, Adam, learning rate schedules, label smoothing, mix-precision)