CS 554: Computer Vision

Spring 2020

• Instructor: Hamdi Dibeklioglu
• Office hours:  random and by appointment in EA-512
• Class hours:
• Monday 10:40-12.30; Thursday 8:40-10:30.
• While every other week we will have 2+2 hours of lectures, other weeks there will be one 2-hours lecture. Please see the schedule below for the dates of the lectures.
• Class room:
• EA-502

UPDATES / NEWS:

• Project presentations will be on 21 May 2020. Duration of your project presentation has to be 10 minutes at most. Although your project submission will be later than your project presentation, you are expected to present a working system with a decent amount of work (together with the final submission, work described in the presentation will also be considered in terms of grading).
  
• Project submission deadline has been extended to 5 June 2020.
• Please follow this link to access the online exam protocol. (Accessible only within Bilkent network. Use VPN to access from home.)
• Duration of your literature survey presentation has to be 10 minutes at most. Please see the Literature Survey and Presentation section below.
• Project Progress Report submission deadline has been extended to 23 April 2020.
• Project submission deadline has been extended to 12 May 2020.
• Homework submission deadline has been extended to 17 April 2020.
• Weights of the assessment methods have been updated as discussed in the class. Please see the Assessment Methods section below.
• Homework details have been announced, please see the Homework section below.
• Important dates have been updated, please see the Important Dates section below.
• Due to the transition to online education:
• Midterm exam has been postponed indefinitely.
• Project progress presentations have been cancelled. However, you still need to submit your project progress report.
• Attendance requirement of the course has been lifted, however, in-class participation and attendance still have a 5% impact on your grade.
• During the online lectures your attendance will be tracked through Zoom. Therefore, please make sure to set your participant ID as your NAME & SURNAME.
• When you submit your reports for survey, homework, project progress, and project, please make sure that you use the required keyword in the subject line of the corresponding email. For the subject line keywords please see the Important Dates section below.
• Online lectures have been started as of 23 March 2020.
• In the website, it was indicated that the surveys should be related to deep learning, which is wrong (typo). Survey should be related to computer vision (methodologies, applications, etc.). Deep learning can be a part of it but it should not be the main focus.
• Expected number of papers for the literature surveys has been reduced to 10.

• R. Szeliski. Computer Vision: Algorithms and Applications, Springer Science & Business Media, 2010. [Available Online] 
• D.A. Forsyth and Jean Ponce. Computer Vision: A Modern Approach, Prentice Hall Professional Technical Reference, 2002.
• I. Goodfellow, Y. Bengio, A. Courville. Deep Learning, MIT Press, 2016. [Available Online]

Assessment Methods:

Any of the following will directly result in an F grade:

• not submitting a project or homework (including report),
• not presenting a survey on the pre-scheduled date,
• being absent in the midterm,
• being absent in a project presentation,
• missing more than 12 lecture hours.

Prerequisites:

• Basic calculus and linear algebra.
• Basic probability theory and statistics.
• Good programming skills.

Passing Grade: No predetermined grade to pass the course.

Makeup Policy: Medical report holders will be entitled for the midterm make up. Makeup exam will be comprehensive.

Homework:
Please follow this link to access the homework details. Homework details/materials are accessible only within Bilkent network. Use VPN to access from home.

Literature Survey and Presentation:

• Groups of two students will choose a topic related to computer vision, and prepare a short survey on it.
• Surveys should be based on about 10 papers (report: 5 pages max.).
• You will make a presentation on your survey in class. The presentation should be in parallel with your report. Duration of your presentation may be 10 minutes at most.
• Survey topics should be confirmed first. Very similar topics to others’ will not be allowed (priority: first come, first served).
• Your chosen survey topic and a few lines explanation (indicating group members) should be sent to dibeklioglu@cs.bilkent.edu.tr by 20 February 2020, 23.59 (Turkey time).

Project:

• By groups of two students.
• Projects related to your research topics are encouraged.
• Build a “real” computer vision application and test it on some data.
• You may re-use existing code, but indicate what you code you have re-used and what code you have developed yourself.
• Three stages:
• Proposal: one-page description of the project topic and the planning (indicating group members) for the project should be sent to dibeklioglu@cs.bilkent.edu.tr by 24 February 2020 (23:59 Turkey time)
• Progress report & presentation (report: 2 pages max.)
• Final report & presentation (report: 4 pages max.)
• Examples of projects:
• Constructing panorama or 3D reconstruction based on a sequence of images
•  Performing face verification for automatic passport control
• Recognizing the identity or expression of faces
• Recognizing gestures for communication via sign language
• Recognizing or detecting objects in images (Pascal VOC / ImageNet)
• Segmenting parts in medical images
• Performing restoration of old, deteriorated photographs
• Performing automatic morphing of images
• Performing video stabilization using object tracking
• Identifying the writer of a piece of handwriting

Template for the Reports:
All reports (including homework report) must be prepared using the IEEE double-column transactions article template.

Important Dates:

Tentative Schedule & Lecture Notes:
Lecture notes below are downloadable only within Bilkent network. Use VPN to access from home.