Unless otherwise noted, all project items are due by 11:59pm Pacific Time.
Deliverable
Weight
Due Date
Late Days
Project Proposal
1%
Apr 23
Yes
Milestone 1: Problem + Related Work
3%
May 15
Yes
Milestone 2: Technical Approach
3%
May 22
Yes
Milestone 3: Preliminary Results
3%
May 29
Yes
Final Report
20%
Jun 05
No
Poster Session (in person) + Poster PDF & Code (submit online)
5%
Poster Session: Jun 10; Submitting PDF and Code: Jun 09 11:59pm Pacific Time
No
Overview
The Course Project is an opportunity for you to apply what you have learned in class to a
problem of your interest. Potential projects usually fall into these two tracks:
Applications.
If you're coming to the class with a specific background and interests (e.g. biology,
engineering, physics), we'd love to see you apply vision models learned in this class to problems related to
your
particular domain of interest. Pick a real-world problem and apply computer vision models to solve it.
Models.
You can build a new model (algorithm) or a new variant of existing models,
and apply it to tackle vision tasks. This track might be more challenging, and sometimes
leads to a piece of publishable work.
One restriction to note is that this is a Computer Vision class, so your project should
involve pixels of visual data in some form somewhere. E.g. a pure NLP project is not a good
choice, even if your approach involves ConvNets. Related areas like shape analysis which are important part of
vision conferences, will be allowed.
We have compiled a list of project ideas for inspiration (TBD) that combine recent trend and interesting
applications. Note that you do not need to pick one from here. Rather, these can be served as starting points
for you to find the ideas that excite you.
To get a better feeling for what we expect from CS231n projects, we encourage you to take a
look at the project reports from previous years:
For applications, this type of projects would involve careful data preparation, an appropriate
loss function, details of training and cross-validation and good test set evaluations and model
comparisons. Don't be afraid to think outside of the box. Some successful examples can be found
below:
ConvNets also run in real time on mobile phones and Raspberry Pi's - building an interesting
mobile application could be a good project. If you want to go this route you might want to
check out PyTorch Mobile, TensorFlow Lite or
Caffe2 iOS/Android integration.
You might also gain inspiration by taking a look at some popular computer vision datasets:
SA-1B: dataset of a large number of images
and segmentation masks to segment objects in those images
COCO: large-scale object detection, segmentation, and captioning
dataset
Open Images: a dataset of
~9M images annotated with image-level labels, object bounding boxes, object segmentation masks, visual
relationships, and localized narratives
Cityscapes Dataset: This dataset focuses on semantic
understanding of urban street scenes, with pixel-level annotations for various object classes such as cars,
pedestrians, and roads
DeepFashion: a large-scale clothes
dataset containing over 800,000 diverse fashion images annotated with bounding boxes, clothing categories, and
attributes
You can work in teams of up to 3 people. We do expect that projects done with
3 people have more impressive writeup and results than projects done with fewer people. However, there are
baseline requirements for a complete paper that have historically been challenging for individuals to meet
without prior experience or additional guidance. To get a sense for the scope and expectations for projects,
have a look at project reports from previous years.
While we encourage that you work in teams, you may also work
alone.
Honor Code
You may consult any papers, books, online references, or publicly available implementations for
ideas and code that you may want to incorporate into your strategy or algorithm, so long as you
clearly cite your sources in your code and your writeup. However, under no circumstances may you
look at another group’s code or incorporate their code into your project.
If you are combining your course project with a project from another class, you must obtain permission from the
instructor of the other class.
You DO NOT need to get prior approval from the CS231n staff. However, in your Project Proposal, Milestone, and
Final Report, you must clearly specify
the UNIQUE portion of the project that is being counted for CS231n. You must prepare separate reports for each
course, and submit your final report for the other course as well.
Remember, it is an honor code violation to use the same final report PDF for multiple classes.
Generative AI Use: The use of generative AI to produce code for a project is subject to the same
guidelines on the use of publicly available sources. All use should be explicitly documented and included within
the final submission. This includes plans, prompts, transcripts as well as documentation marking
every
AI-generated artifact. Ultimately, group members are responsible for proper attribution for all artifacts in the
project.
The written component of the assignment is intended to frame your thinking and argue for the unique and notable
contribution of your project. As such, the use of generative AI to write components of the final report would be
against both the spirit of the project and the Honor Code. Generative AI may, however, be employed as an editing
and formatting tool.
The project proposal should be one paragraph (200-400 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)?
If you are combining this project with another course/research project, what is the unique portion of the
project that is counted towards this class?
Submission:
Please submit your proposal as a PDF on Gradescope. Only one person on your team should submit.
Please have this person add the rest of your team as collaborators as a "Group Submission".
Project Milestone Check-Ins
This year, we are introducing three milestone check-ins to help you stay on track and receive structured
feedback throughout the project.
Each check-in consists of a 10-minute discussion with course staff during TA office hours
(see Office Hours). No scheduling is required. Please come prepared with a
best-effort version of your progress.
Check-in Format
Each check-in requires a short presentation (2–5 slides). During the check-in, you should clearly
present your current progress.
Slides are required to help communicate your work effectively.
Slides should be submitted to Gradescope prior to your check-in.
All group members are expected to attend and participate.
Course staff will ask questions.
Milestone Schedule
Please plan your project progress accordingly and complete your check-ins in a timely manner.
Milestone 1 (Problem + Related Work): May 15
Milestone 2 (Technical Approach): May 22
Milestone 3 (Preliminary Results): May 29
Milestone Breakdown
Milestone 1 — Problem + Related Work (May 15)
This milestone is about making sure your problem is well-defined and grounded in prior work.
You should clearly describe what problem you're solving, what data you plan to use (if applicable),
and what success would look like. It's also important to outline how you plan to evaluate your method
(e.g., metrics, baselines, or benchmarks).
In addition, please include a brief discussion of a few (at least 3) relevant papers and how your
project relates to them.
Suggested slides: problem motivation, dataset/evaluation setup, expected outcomes, and related
work positioning. If you already have an initial idea or hypothesis, feel free to include that as well.
Milestone 2 — Technical Approach (May 22)
The goal of this milestone is to solidify your method and plan for implementation.
You should present your proposed approach, including the key design choices and the intuition behind them.
It would also be helpful to explain why you expect your method to work, especially in comparison to your
baselines.
Please also describe how you plan to use your dataset, what your experimental setup will look like,
and how you'll evaluate performance.
Suggested slides: method overview (diagrams encouraged), design intuition, baselines, and
experimental setup, along with your current implementation plan or progress.
Milestone 3 — Preliminary Results (May 29)
This milestone focuses on what you've achieved so far.
You should present initial results, ideally with some quantitative evaluation (figures or tables),
and compare them against your baselines. We're especially interested in your analysis—what's working,
what isn't, and whether the results align with your expectations.
Please also briefly discuss limitations and your next steps.
Suggested slides: results, comparisons, analysis/insights, limitations, and next steps.
Grading
Each milestone will be evaluated based on the following criteria:
Progress (1%):
Demonstrates meaningful progress toward the project goals, including implementation, experiments,
or concrete results appropriate to the stage of the project.
Clarity (1%):
Presents ideas clearly and logically, with well-structured slides and effective communication
of key concepts, methods, and findings.
Robustness (1%):
Shows thoughtful reasoning and technical soundness, including validation of approaches,
consideration of limitations, and ability to justify design choices.
Final Report
Your final write-up is required to be between 6 - 8 pages using the
provided template,
structured like a paper from a computer vision conference (CVPR, ECCV, ICCV, etc.).
Please use this template so we can fairly judge all student projects without worrying about
altered font sizes, margins, etc. After the class, we will post all the final reports online
so that you can read about each others' work. If you do not want your writeup to be posted
online, then please let us know via the project registration form.
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.
Refer to Ed for more fine-grained details and
explanations of each separate section.
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
Related Work (10%):
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 for 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:
Source code (if your project proposed an algorithm, or code that is relevant and important
for your project.).
Cool videos, interactive visualizations, demos, etc.
Examples of things to not put in your supplementary material:
The entire PyTorch/TensorFlow Github source code.
Any code that is larger than 10 MB.
Model checkpoints.
A computer virus.
Submission:
You will submit your final report as a PDF and your supplementary material as a separate PDF
or ZIP file. We will provide detailed submission instructions as the deadline nears.
Additional Submission Requirements:
We will also ask you do do the following when you submit your project report:
Your report PDF should list all authors who have contributed to your work; enough to
warrant a co-authorship position. This includes people not enrolled in CS 231N such as
faculty/advisors if they sponsored your work with funding or data, significant mentors (e.g.,
PhD students or postdocs who coded with you, collected data with you, or helped draft your
model on a whiteboard). All authors should be listed directly underneath the title on your PDF.
Include a footnote on the first page indicating which authors are not enrolled in CS 231N. All
co-authors should have their institutional/organizational affiliation specified below the title.
If you have non-231N contributors, you will be asked to describe the following:
Specify the involvement of non-CS 231N contributors
(discussion, writing code, writing paper, etc). For an example, please see the author
contributions for AlphaGo (Nature, 2016).
Specify whether the project has been submitted to a peer-reviewed conference or journal.
Include the full name and acronym of the conference (if applicable). For example: Neural
Information Processing Systems (NIPS). This only applies if you have already
submitted your paper/manuscript and it is under review as of the report deadline.
Any code that was used as a base for projects must be referenced and cited in the body of the paper.
This includes CS 231N assignment code, finetuning example code, open-source, or Github
implementations. You can use a footnote or full reference/bibliography entry.
If you are using this project for multiple classes, submit the other class PDF as well.
Remember, it is an honor code violation to use the same final report PDF for multiple classes.
In summary, include all contributing authors in your PDF; include detailed non-231N co-author
information; tell us if you submitted to a conference, cite any code you used, and submit your
dual-project report (e.g., CS 230, CS 231A, CS 234).
Poster Session
We will hold a poster session in which you will present the results of your projects.
Date: Jun 10
Time: 12:00-3:30 PM
Location: TBD
Who: Student groups must present in-person at the poster session, unless approved by course staff
beforehand to present online. Stanford students, faculty, and guests from industry are welcome!
Students: We will provide foam poster boards and easels.The foam boards we will provide have the size of 30x40
inches, so please print your poster <= than this size but>= 20x30 inches. Our recommended size is 24x36 inches.
You may print your poster in landscape or portrait orientation.
Frequently Asked Questions
Where can I print my poster?
Several options are listed below. These are just examples; they are not the only options. Please verify the
turnaround time yourself and plan ahead since the printing services may become occupied as the day of the
event approaches.
Lathrop Library’s Tech Desk: Approximately 3-day turnaround.
FedEx: Approximately 2-day turnaround.
Walgreens: Approximately same-day pickup.
Biotech Productions: Approximately same-day delivery.
Staples: Approximately same-day pickup.
Can I print my poster on 8.5x11 inch pieces of paper and tape them together? Yes, but we encourage you
to print out one full poster. If you do print sections and tape them together, make sure that all the content
is still legible and fits on a 30x40 foam board.
