Welcome
Course description
Almost every other day, we hear of innovations in the field of visual recognition. Automatic classification of images, object detection, action recognition in videos, scene understanding by autonomous cars and object tracing by drones are just a few examples of the what can be achieved with visual recognition methods. Recent developments in neural networks (aka deep learning) have significantly advanced the visual recognition field. The goal of this course is to teach about cutting-edge deep learning architectures for visual recognition, and how to implement, train and debug neural networks. Students will gain theoretical knowledge, information on the latest research in the field, and will gain practical skills.
Agenda
- Introduction to Visual Recognition.
Grading
Final grade: 50% Exam + 50% laboratory assignments. Both have an equal impact on the final grade. You need to score at least 50% in each.
Graded laboratory assignments are available on moodle. Late submission policy: (1) up to 1h after the deadline - the score will be multiplied by 0.9. (2) after 1h, but before the hard deadline - the score will be multiplied by 0.6. (3) no submission allowed after the hard deadline. Information about the hard deadline is available for each task on Moodle; otherwise, you need to submit the assignment before your last laboratory class.