Deep Learning for Computer Vision

This advanced course explores the principles, techniques, and applications of deep learning in computer vision. Students will learn to design, train, and validate neural networks for image classification, object recognition, semantic segmentation, and other computer vision tasks. They will also study advanced techniques for improving deep learning model performance and visualizations to provide guidance for further model development. By the end of the course, students will be equipped to apply deep learning techniques to solve real-world problems in various domains.

The course is managed via the Moodle learning platform. All documents and further information can be found in the Moodle course Deep Learning for Computer Vision.

Please notice: The materials for our lectures and exercises are only available through the network of the Bauhaus-Universität Weimar.

Integrated lecture

Lectures

  1. Organisation, history and perceptron
  2. Optimization and regularization
  3. Convolutional neural networks
  4. Image classification and transfer learning
  5. Architectures
  6. Transformer I.
  7. Transformer II.
  8. Object detection
  9. Semantic and instance segmentation
  10. Probabilistic generative models
  11. Deep learning for image matching
  12. 3D deep learning applications I
  13. 3D deep learning applications II

Assignments

  1. Basic Deep Learning Workflow
  2. Regularization and modularization
  3. Transformer vs CNN
  4. Object Detection
  5. Probabilistic generative models
  6. 3D deep learning applications

Exam

Written exam
 

  • Date: will be announced later
  • Place: will be announced later
  • Auxiliary resources: none

Preparation material

  • Old exam samples