CPTS 541 – Computer Vision

Course Overview

CPTS 541 – Computer Vision introduces fundamental principles and modern techniques for analyzing and interpreting visual data (e.g., images and videos). The course covers:

  • Core low-level vision techniques (image filtering, feature detection)
  • Foundations of machine learning for perception
  • Deep neural network architectures and applications in vision

The emphasis is on both conceptual understanding and practical implementation of vision systems using state-of-the-art methods.

Learning Outcomes

  • Understand classical computer vision algorithms and representations
  • Apply machine learning models to visual tasks
  • Design and implement deep learning solutions for detection, segmentation and recognition

Syllabus

Lecture Schedule

Lecture Topic Slides
1 [0] Syllabus and Overview Slides
2 [CV] Image Classification Slides
3 [CV] Image Processing Slides
4 [CV] Image Descriptors Slides
5 [ML] What Is Learning Slides
6 [ML] Linear Models Slides
7 [ML] MLE and PAC Learning Slides
8 [ML] Optimization Slides
9 [NN] NN Basics Slides
10 [NN] Compositing Units in NN Slides A, Slides B
11 [NN] Backpropagation Slides
12 [NN] MLP Softmax Classifier Slides
13 [CNN] Convolutional Layer and CNN Slides
14 [CNN] CNN Architectures Slides A, Slides B
15 [CNN] Practical Training of CNN Slides
16 [ModernNN] Transformer Slides
17 [ModernNN] ViT Slides
18 [OD] Ojbect Detection 1 Slides
19 [OD] Ojbect Detection 2  
20 [Seg] Segmentation Slides
21 [Video] Vdieo Classification Slides
22 [Video] Modern Video Classification Slides
23 [GenAI] Image and Video Generation 1 Slides
24 [GenAI] Image and Video Generation 2  
25 [FM] Foundation Models Slides
26 [FM] Foundation Models