Typically, projects will involve analytic, implementation and evaluation components.
EECS 4422 students may decide to implement and evaluate an algorithm from the literature. If source code is available online, you must document this and identify clearly how your project extends this existing source code.
EECS 5323 students are expected to extend or innovate substantially upon published algorithms, or implement and compare the performance of two algorithms on the same problem.
Inspiration: Consider the following when selecting a project topic:
If you are affiliated with a research lab, considering selecting a problem domain that your lab is active in. Consult with the people in the lab about your project topic.
Survey some of the algorithms and papers mentioned in the textbook (Szeliski). Read ahead to future chapters to find a topic that excites you.
-
Projects will consist of four stages, as follows. Please see the Schedule for deadlines.
Project Idea: The student will propose a specific project idea in the form of a short paragraph, submitted via Moodle. The instructor will either accept the topic (possibly with modifications) or raise issues that the student will address in revision of the project idea. The final project selection is subject to the instructor's approval.
Proposal: The proposal is a one-page document submitted via Moodle that includes: (i) Motivation: why is the topic interesting? (ii) Datasets: what datasets will you use to study the problem? (iii) Proposed methods: what algorithm(s) do you plan to implement? (iv) Evaluation methodology and (v) Proposed timeline for completion.
Presentation/Demo: A brief slide presentation on the project will be made during one of the last two lecture meetings. There will also be an opportunity to demo the project during the final lab.
Final Report: Maximum 8 pages, excluding references, in
CVPR 2018 format. More guidance on the structure of the final report will be provided. Please consult these
guidelines when preparing your report.