CSC2547 involves a course project in which you will implement a research idea on the topic of 3D and Geometric Deep Learning or related areas. Any of the broad topic descriptions on the course website, under which weekly readings are listed, can act as a good starting point for picking a project. The purpose of the final project is to give you the chance to spend a significant amount of time focusing on a single research direction. The types of projects that we envision include the following:
- Implement the main algorithm described in one of the papers listed on the course website, try to replicate the results, and run it in 2-3 new scenarios.
- Provide an empirical evaluation and comparison of at least three algorithms from the papers in the reading list, on 1-2 illustrative scenarios.
- Extend the main algorithm described in one of the papers listed on the course website in a non-trivial way, and evaluate it on 1-2 new scenarios.
- Invent a new algorithm, and provide sufficient evaluation to demonstrate the merit of the idea, at minimum 1-2 scenarios.
You can get full marks for a project in any of these categories. You are not expected to produce a novel research idea, although courses like this are meant to create the conditions for students to attempt it. We encourage you to try.
Collaboration: You are encouraged to form groups of 2-3 for the course project, but it is also acceptable to work alone. If you do not know anyone in class, feel free to post a message on Piazza.
- Proposal due on Feb 16 at 5PM.
- Midterm progress report due on March 16 at 5PM.
- In-class presentation on April 6.
- Final report and code due on April 14 at 5PM.
Proposal (5%, Feb 16)
You are expected to describe a well-defined research goal in the proposal. When choosing this goal try to identify the minimum viable objective that you think is likely to work and you can accomplish, just to get you started, some nice-to-haves that you will do provided there is time, and a short review of related work.
The definition of your research project may change during the course of a month and a half that you will be working on your project, but your proposal should be as specific and well-defined as possible, otherwise we cannot provide helpful feedback. If you are unsure about your plans, contact the instructor before the proposal due date.
Proposals need not be based only on papers covered in class by the due date. Students are encouraged to look further ahead in the schedule and to start planning their project definition well ahead of the due date.
Proposals are limited to 2 pages, with the following suggested structure:
- 1/4 page for abstract/introduction to the problem,
- 1/2 page for related work,
- 1/2 page for the method,
- 1/2 page for proposed evaluation,
- 1/4 page for references.
Proposals should follow the template provided by Neural Information Processing Systems (NeurIPS). Proposals will be submitted to Quercus.
Student co-authors should be listed alphabetically in the proposal.
Midterm Progress Report (5%, Feb 28 11:59PM)
This is a three page document. The first two pages contain a copy of your project proposal. The other page includes: 3/4 page status update, presenting what you have accomplished so far (include figures and results), and 1/4 page describing your next steps.
Progress reports will be submitted on Quercus.
Can I use the same project for more than one class?
Yes, but you need to let the instructor (of all involved courses know ahead of time). If this is part of two courses, naturally more work/progress/sophistication is expected. If this is done as a part of the team -- would there be other members not in the course. Since it would be hard to assign credit, the latter situation is discouraged.
Project Group Size?
More than three is discouraged. If you still intend to work in a team of >3 please see instructor with an explanation why you think it is necessary. Groups of size 1 are permitted on a case by case basis.
Can I extend a project I completed in a previous class? Yes, you are welcome to do this as long as you provide your final report from that class and include an appendix to the proposal that clarifies what is being added to the previous project.
Can I extend a project I completed or am working on as part of my research/thesis?
Yes, you are welcome to do this as long as you include an appendix to the proposal that clarifies what is being added to the research you have done so far outside this course.
I need a GPU but I don’t have access to one. What should I do?
Let us know early on if this is a problem. You should also look into Google Colab, and any GPU desktops provided by your department (if any).
Presentation (15%, Apr 6)
[more info soon]
Final Report and Code (25%, Apr 14)
[more info soon]