Class Project:

The class project carries 30% of your total grade. The final project can be related to your research area. However, do not submit anything you have completed before attending the course. You also should not submit a project that is largely a collaborative effort with people outside the course. The final project requires a proposal, a poster/presentation, and a final report per team.

We encourage you to reach out to TAs you are interested in working with.

Following are the project guidelines to be followed during the complete semester.

  1. A team should not have more than 4 members. Recommended size is 3.
  2. There are four components:
    a. Project Proposal
    b. Mid-semester milestones
    c. Presentation
    d. Final report

Timeline and deadlines:

Project Proposal: Sunday, February 28, 2021
Milestone 1 review: Thursday, March 18, 2021
Milestone 2 review: Tuesday, April 20, 2021
Presentation: Tuesday, May 11, 2021
Final report: Tuesday, May 18, 2021

Project Proposal (6%):

A canvas assignment will be made available for a project proposal. Please follow the guidelines given below.
The project proposal should be one page at a maximum (400-800 words). Your project proposal should describe:
What is the problem that you will be investigating? Why is it interesting?
What reading will you examine to provide context and background?
What data will you use? If you are collecting new data, how will you do it?
What method or algorithm are you proposing? If there are existing implementations, will you use them, and how?
How do you plan to improve or modify such implementations? You don’t have to have an exact answer at this point, but you should have a general sense of how you will approach the problem you are working on.
How will you evaluate your results? Qualitatively, what kind of results do you expect (e.g. plots or figures)?
Quantitatively, what kind of analysis will you use to evaluate and/or compare your results (e.g. what performance metrics or statistical tests)?
Who are the members of your team? Who is your TA adviser? You should have an idea of the division of labor between the team members.
Only one person from each group/team should submit the proposal to Canvas. The submission should be ONE single page PDF format. Teams should have a title, the name of their team members, and their TA adviser.

Milestone 1 review (2%):

Teams will meet with their TAs to report the progress made until that point.
The team should have a clear idea about the dataset and methods they are going to implement.
The team needs to present their plan and future goals.

Milestone 2 review (2%):

The team should present their preliminary results.
The team should also discuss their strategy to improve the results and their plan for presentation.

Presentation (10%):

All the teams need to present their project to the class, TAs and the instructor.
The presentation must not extend over 5 minutes. Due to time constraints, no one will be allowed to go over time.
There will be 1 minute towards the end (after the presentation) for any questions and transition.

The presentation should have the following general format :
Introduction/Motivation
Dataset
Methodology/Approach
Results
Conclusions

The above is just a guideline. You may deviate from it if you think that is appropriate.
The presentations will happen on the same zoom link as the regular class.
A separate canvas assignment will be created to submit the presentation in the .pdf format. This assignment will be due on the presentation day at 2:00 PM.
There will be no posters required this semester. Only the presentation is required.

Final report (10%):

We know that most students work very hard on the final projects, and so we are extremely careful to give each writeup ample attention and read and try very hard to understand everything you describe in it.

Your final report is required to be between 6 - 8 pages using the provided template on canvas, structured like a paper from a computer vision conference (CVPR, ECCV, ICCV, etc.). Please use this final submission template so we can fairly judge all student projects without worrying about altered font sizes, margins, etc. We will allow for extra pages containing only references. If you did this work in collaboration with someone else, or if someone else (such as another professor) had advised you on this work, your write-up must fully acknowledge their contributions. For shared projects, we also require that you submit the final report from the class you’re sharing the project with. Please include a section that describes what each team member worked on and contributed to the project.

The following is a suggested structure for your report, as well as the rubric that we will follow when evaluating reports. You don’t necessarily have to organize your report using these sections in this order, but that would likely be a good starting point for most projects.

Title, Author(s)

Abstract:

Briefly describe your problem, approach, and key results. Should be no more than 300 words.

Introduction (10%):

Describe the problem you are working on, why it’s important, and an overview of your results

Discuss published work that relates to your project. How is your approach similar or different from others?

Data (10%):

Describe the data you are working with for your project. What type of data is it? Where did it come from?
How much data are you working with? Did you have to do any preprocessing, filtering, or other special treatment to use this data in your project?

Methods (30%):

Discuss your approach to solving the problems that you set up in the introduction. Why is your approach the right thing to do? Did you consider alternative approaches? You should demonstrate that you have applied ideas and skills built up during the quarter to tackling your problem of choice. It may be helpful to include figures, diagrams, or tables to describe your method or compare it with other methods.

Experiments (30%):

Discuss the experiments that you performed to demonstrate that your approach solves the problem. The exact experiments will vary depending on the project, but you might compare with previously published methods, perform an ablation study to determine the impact of various components of your system, experiment with different hyperparameters or architectural choices, use visualization techniques to gain insight into how your model works, discuss common failure modes of your model, etc. You should include graphs, tables, or other figures to illustrate your experimental results.

Conclusion (5%):

Summarize your key results - what have you learned? Suggest ideas for future extensions or new applications of your ideas.

Writing / Formatting (5%):

Is your paper clearly written and nicely formatted?

Supplementary Material, not counted toward your 6-8 page limit and submitted as a separate file. Your supplementary material might include:

  1. Source code (if your project proposed an algorithm, or code that is relevant and important for your project.).
  2. Cool videos, interactive visualizations, demos, etc.
  3. Examples of things to not put in your supplementary material:
  4. The entire PyTorch/TensorFlow Github source code.

It should not include:

  1. Any code that is larger than 10 MB.
  2. Model checkpoints.
  3. A computer virus.

Please include a zip file containing a pdf of the report and supplementary material, preferably a link to a Github repository with the code for your final project. You do not have to include the data or additional libraries (so if you submit a zip file, it should not exceed 5MB). If you have a private repository, please add your mentor as a member of the repository (please contact your TA individually to ask for his or her GitHub ID)