Course Projects (tentative)

If you are enrolled in the course for four credits, you are required to complete a project for 25% of your grade.

Projects can be done individually or in groups of up to three people. Feel free to use Campuswire to search for teammates. Project formats include, but are not limited to, the following:

1. Implementation or demo: Find a research paper related to the topics covered in class and implement their method. You may want to follow the spirit of recent ML reproducibility challenges. Alternatively, feel free to apply existing methods to new datasets, compare and contrast several methods, adapt or modify them.

2. Kaggle competition: Find a competition on Kaggle (or some other public challenge) and implement a deep learning system for it (it is not necessary to actually enter the competition, or to use all of the data if it is too large).

You will be required to submit a project proposal, and the final project deliverable.

Proposal: due Oct 19, 11:59:59PM

Your proposal should be up to two pages and address each of the following:

1. An informative title, that indicates what the project is about. Please don't just say “Course Project”, etc.

2. List of group members.

3. Project description and goals: Describe what you plan to do in the project and how. You can change later as you go along, but try to think this through as much as possible in advance. Identify the desired final outcome and pose maximum and minimum goals.

4. Resources: Specify what code, data and references you plan to use or build upon.

5. Member roles: Indicate which project component each group member will be responsible for and how the group will interact.

6. Relationship to your background: Describe how the proposed project relates to your background or level of knowledge. Which techniques, software packages, etc., are you already familiar with, and which ones will be new to you? Also discuss relationship to any work done outside of this course (e.g., RA, thesis research, project in a different class). Your CS 444 project can be synergistic with what you have done or are doing elsewhere, but it should not consist entirely of work you would be doing anyway.

Note: We will provide feedback on the proposal but not a formal grade. Late project proposal submissions will incur a 10% per day penalty on the final project grade.

Final report, video and code: due Dec 11, 11:59:59PM

Final deliverables include:

1. Final Report: A 6-page final report. Here is an outline to follow for the report:

   1. An informative title, that indicates what the project is about. Please don't just say “Course Project”, etc.

   2. Introduction (why you did what you did): Define and motivate the problem, discuss background material or related work, and briefly summarize your approach.

   3. Approach (what you did): Include any formulas, pseudocode, diagrams – anything that is necessary to clearly explain your system and what you have done. If possible, illustrate the intermediate stages of your approach with results images.

   4. Results (how well it worked): Clearly describe your experimental protocols. If you are using training and test data, report the numbers of training and test images. Be sure to include example output figures. Quantitative evaluation is always a big plus (if applicable).

   5. Discussion and conclusions (what did you learn): Summarize the main insights drawn from your analysis and experiments. You can get a good project grade with mostly negative results, as long as you show evidence of extensive exploration, thoughtfully analyze the causes of your negative results, and discuss potential solutions.

   6. Statement of individual contributions.

   7. References: including URLs for any external code or data used.

2. 5-minute Narrated Video that explains your project and summarizes the points above. You can upload the video to YouTube (or other such external repositories) and include a link in your report.

3. Code: A zip file of your source code to be uploaded to Gradescope. We are looking for only the most important code that you wrote yourself for the project, not any external libraries. We do not plan to run the code, but want to see it to be able to verify that you actually did the work you claim to have done.

Grading

Grades will be based on the quality of the project (originality, thoroughness, extent of analysis, etc.) and the clarity of the written report and presentation. More will be expected of larger groups. You can still get a good grade if your ideas do not work out, as long as your presentation and report show evidence of extensive analysis and exploration, and provides thoughtful explanations of the observed outcomes.

Submission Instructions

Project proposals and final reports all should be in PDF form and must be submitted to Gradescope. Only one submission is required per group, though you must add group members on the submission (there is a way to do this in Gradescope). You must use the template from CVPR (use the non-anonymous version). Project proposal should be up to two pages, and final report should be between 5 to 6 pages. References and additional supporting figures can go beyond the page limit. We may or may not read content beyond the page limit.

Adapted from Lana Lazebnik.