Computer Vision
Your browser doesn't support speech here. You can still read everything, or try Chrome, Edge or Safari.

← All courses

Course 6 of 10 · Intermediate → Advanced

Computer Vision

Images, detection and segmentation. Images as data and augmentation, classification with pretrained CNNs, object detection, segmentation, Vision Transformers and CLIP, robustness and fairness.

How this course works

Welcome

  • Level: Intermediate → Advanced. You need: Deep Learning.
  • Before you start: the Deep Learning course, at least up to CNNs and transfer learning.
  • Its game season follows the vision projects of the Applied AI team.
  • Pick a topic from the sidebar; they go in order. Press ▶ Play this topic to hear a lesson read aloud, or 🔊 Explain on one section.
  • Topics climb from Beginner to Intermediate · Maths, Advanced and Code; use the Show chips to hide levels you don't need. Most have a Watch it animation, Try it demos and runnable code examples, and every topic ends with a quiz: answer it to mark the topic done ✓.
  • Stuck? Press 💬 Ask the AI tutor: a small free AI model that runs on your own device and answers from the course.
  • Progress is saved in this browser and shared across all the courses on this site.

Learning path: 🐍 Python → 🗄️ SQL & Databases → ∑ Maths for AI → 📈 Machine Learning → 🧠 Deep Learning → 👁️ Computer Vision → 💬 Natural Language Processing → ✨ Generative AI & LLM Apps → 🚀 Flask & Deployment → 🔬 Becoming an AI Researcher

Computer Vision

1. Computer Vision: Start HereThe main vision tasks, what a junior CV engineer does, the tools of the field, and how this track and its game season are organised.2. Images as Data, Preprocessing & AugmentationPixels, channels and colour spaces, resizing and normalisation, file formats including medical images, and data augmentation that keeps labels correct.3. Image Classification in PracticeChoosing and fine-tuning a backbone, imbalanced and multi-label data, evaluation and calibration, and seeing what the model looks at with Grad-CAM.4. Object DetectionBoxes and their formats, IoU, anchors and one- vs two-stage detectors, non-maximum suppression, mean average precision, and the modern YOLO and DETR families.5. 🎮 Milestone C1: Reading the referral formsBuild the vision pipeline that reads Riverside's scanned referral forms: decide the tasks, write augmentation that keeps boxes correct, check what the document classifier looks at and whether its confidence is honest, and evaluate the field detector with mAP. Includes 3 hands-on Python coding tasks (NumPy), checked by automated tests.6. Image SegmentationLabelling every pixel: semantic and instance segmentation, the U-Net encoder-decoder, Dice and IoU, losses for small structures, and medical-imaging practice.7. Vision Transformers, Self-Supervision & CLIPImages as sequences of patches, how ViTs compare with CNNs, self-supervised pretraining (DINO, masked autoencoders), and CLIP for zero-shot classification and search.8. Robustness, Fairness & Deploying Vision ModelsDistribution shift between devices and sites, shortcut learning, adversarial examples, fairness across skin tones and groups, and taking a model to phones, edge devices and production.9. 🎮 Milestone C2: The wound-care appRiverside's community nurses want an app that outlines a wound in a photo and tracks healing. Choose a segmentation approach, check metrics and U-Net shapes, test whether CLIP can sort wound types without labels, and decide where the app is ready, clinic by clinic and patient by patient. Includes 3 hands-on Python coding tasks (NumPy, scikit-learn, pandas), checked by automated tests.10. ✅ Checkpoint: Computer Vision trackA mixed quiz on the whole Computer Vision track. Pass mark: 7 of 9 on the first try.
When you finish

Next course

Ready