CSE615: Advanced Computer Vision

Instructors: Prof. Dimitris Samaras, Minh Hoai, Habin Ling, Michael Ryoo

Spring 2020: Wednesday 2.30 – 5.20 Room 115, New Computer Science

Course Descriptions

Thu current success of Deep Learning methods in Computer Vision, the availability of larger and more diverse datasets and hardware advances, have generated an explosion of interest in Computer Vision. This course, co-taught by four faculty whose expertise spans the entire field of computer vision, will examine recent advances in computer vision together with fundamental concepts in geometry and physics, and ways that they have been incorporated in deep learning pipelines. The exact syllabus will be posted at the beginning of the course.

 This will be a paper presentation and project based course. Prior exposure to visual computing is necessary. Students should have completed at least one computer vision or machine learning course, and have experience with current deep learning programming environments and computer vision libraries. This course is aimed at PhD students and MS students with strong interest in Computer Vision. MS students can register with instructor permission.

Grading:

The final course grade will be based 10% on in-class participation, 20% on the written critiques, 20% on the paper presentations, and 50% on the term project. You can skip up to 25% of the critiques. Critiques should be written individually and not discussed with classmates before class.

Final projects can be done by one or two people. Two people projects will be scaled accordingly.

Textbook:

(Optional) Computer Vision: Models, Learning, and Inference by S. Prince, Cambridge University Press, 2012

(Optional) Kevin Murphy, Machine Learning: A Probabilistic Perspective http://people.cs.ubc.ca/~murphyk/MLbook/

(Optional) Deep Learning by I. Goodfellow, Y. Bengio, A. Courville, MIT Press 2016.

Class notes and a collection of additional readings from journals and conference proceedings will be available through Blackboard.

Academic misconduct policy:

Don't cheat. Cheating on anything will be dealt with as academic misconduct and handled accordingly. I won't spend a lot of time trying to decide if you actually cheated. If I think cheating might have occurred, then evidence will be forwarded to the University's Academic Misconduct Committee and they will decide. If cheating has occured, an F grade will be awarded. No excuses!

Disability note:

If you have a physical, psychological, medical or learning disability that may impact on your ability to carry out assigned course work, I would urge that you contact the staff in the Disabled Student Services office (DSS), Room 133 Humanities, 632-6748/TDD. DSS will review your concerns and determine, with you, what accommodations are necessary and appropriate. All information and documentation of disability is confidential.

_

Contact info:

    D. Samaras, Tel. 631-632-8464
    email: samaras@cs.stonybrook.edu