Computer Vision with Deep Learning
From image classification to object detection, segmentation, and generative models. Learn how deep learning has transformed computer vision.
Level: Advanced · Category: Computer Vision · Estimated time: 7 hours
Prerequisites
- PyTorch Mastery
Lessons
- CNN Fundamentals — Convolutions, filters, pooling, feature maps, and receptive fields.
- Classic Architectures — LeNet, AlexNet, VGG, ResNet, Inception, and EfficientNet.
- Transfer Learning & Fine-Tuning — Using pre-trained models, freezing layers, and domain adaptation.
- Object Detection: YOLO & R-CNN Family — Anchor boxes, YOLO, SSD, Faster R-CNN, and modern detectors.
- Image Segmentation — Semantic segmentation, instance segmentation, U-Net, and Mask R-CNN.
- Vision Transformers (ViT) — Applying transformers to images, patch embeddings, and ViT variants.
- GANs & Image Generation — Generative adversarial networks, StyleGAN, and image synthesis.
- Diffusion Models — Denoising diffusion, DDPM, Stable Diffusion, and controllable generation.
Related consolidated topics
- Computer Vision Fundamentals: Image classification, object detection, and segmentation from first principles.
Topics covered
cnn, object-detection, image-classification, yolo, gans, vision-transformers, segmentation