Content

Current issues, methods and datasets in computer vision for image classification, object detection, image segmentation, image generation and domain transfer and semi-supervised learning. All lecture material such as slides, recordings, as well as the exercises are available in the lecture moodle.

Programming exercises will be implemented in python and pytorch.

Schedule

• regular Lecture: Monday:  4-6pm, starting on 10.10.2022

• Exercise: Monday, 6-8pm, Start: 10.10.2022

• Both lecture and exercise will also be streamed online via zoom. Please make use of this option in case you feel sick. 

Qualification Goals

• Deep understanding of current computer vision methods for image classification, object detection, image segmentation, image generation, and domain transfer.
• Understand, apply and evaluate current approaches.
• Understanding of the technical principles of computer vision methods.
• Evaluation and discussion of new computer vision problems and methods.

Literature

• R. Szeliski: Computer Vision Algorithms and Applications, Springer, 2010. ISBN: 978-1-84882-934-3. (Online available: http://szeliski.org/Book/).
   

• Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, An MIT press book, 2016