🧠Deep Learning
🖼️
Convolutional Neural Networks
Master CNNs for image classification, object detection, and computer vision tasks
Prerequisites
🌱
Beginner
BeginnerCNN fundamentals
What to Learn
- •Convolution operation intuition
- •Pooling layers and stride
- •Building blocks: Conv → BN → ReLU → Pool
- •Classic architectures: LeNet, AlexNet
- •Transfer learning with pretrained models
Resources
- 📚Stanford CS231n lectures
- 📚PyTorch Vision tutorials
- 📚FastAI practical deep learning
🌿
Intermediate
IntermediateAdvanced CNN architectures
What to Learn
- •VGG, ResNet, and Inception architectures
- •Object detection: YOLO, Faster R-CNN
- •Semantic segmentation: U-Net, DeepLab
- •Data augmentation strategies
- •Fine-tuning and feature extraction
Resources
- 📚Original architecture papers
- 📚Detectron2 documentation
- 📚Papers With Code benchmarks
🌳
Advanced
AdvancedState-of-the-art computer vision
What to Learn
- •Vision Transformers (ViT)
- •Self-supervised visual learning
- •3D vision and point clouds
- •Video understanding models
- •Multimodal vision-language models
Resources
- 📚ViT and CLIP papers
- 📚CVPR/ICCV recent papers
- 📚Segment Anything (SAM) paper