Skip to main content

Advanced Computer Vision

Object detection, segmentation, YOLO, image generation.

Course Duration: 12 hours​

What You'll Learn​

  • Object detection architectures
  • Image segmentation
  • YOLO family
  • Pose estimation
  • Face recognition
  • OCR and document analysis

Prerequisites​

  • CNN fundamentals
  • TensorFlow or PyTorch

Course Modules​

  1. Object Detection Overview
  2. R-CNN Family
  3. YOLO v5/v8
  4. SSD and RetinaNet
  5. Semantic Segmentation
  6. Instance Segmentation (Mask R-CNN)
  7. Panoptic Segmentation
  8. Pose Estimation
  9. Face Detection and Recognition
  10. OCR with Tesseract
  11. Vision Transformers
  12. Project: Real-time Object Detection

Architectures Covered​

  • YOLO v5/v8
  • Faster R-CNN
  • Mask R-CNN
  • U-Net
  • DeepLab