CSC3104 · 9 modules

Computer Vision & Deep Learning

Pixels to production: CNNs, detection, segmentation, transformers and responsible deployment.

Start: Images as Data Mock exam Revision guide
0%
Exam readiness
Not started
  1. 1

    Images as Data

    Represent, inspect & transform image inputs

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  2. 2

    Convolutional Neural Networks

    Understand convolution, pooling & feature maps

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  3. 3

    Training & Evaluation

    Train, validate & diagnose classifier behaviour

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  4. 4

    Transfer Learning

    Adapt pretrained models to a new problem

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  5. 5

    Object Detection

    Find object classes & locations

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  6. 6

    Segmentation

    Predict pixel-level regions

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/1Lab 0/4
    Learn Lab
  7. 7

    ViTs + Multimodal

    Use image–text & transformer-based vision

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab
  8. 8

    Video + Tracking

    Connect detections across time

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/1Lab 0/4
    Learn Lab
  9. 9

    Deployment & Responsible Vision

    Package, benchmark & explain limitations

    0%
    Lesson 0/74 note sectionsCheckpoint —Quiz 0/8Code 0/2Lab 0/4
    Learn Lab