Textbooks

The primary material for this course will be research papers, which will be listed on the schedule page. There is no required textbook for this class. However, the following textbooks are highly recommended and may prove useful:

Required Background

This course assumes a strong proficiency in Python and a solid mathematical foundation, including linear algebra, probability, statistics, and calculus. Prior coursework in machine learning and deep learning is essential, and experience from an undergraduate or master’s level computer vision course is highly recommended.

Given the project-based nature of this course, students must be comfortable independently applying their knowledge to complex problems and clearly communicating their findings. Writing is a key component of all projects.

Resources on reading research papers:

Resources on writing research papers:

Resources on presenting research:

Grading

The grading breakdown for this class is as follows:

  • 100% Project

Note that this class does not have any tests or exams.

The cutoffs for letter grades vary each year, but here are the cutoffs used in a previous offering of the class: A (92), A- (87), B+ (83), B (79), B- (75), C+ (70), C (65), C- (60), D+ (55), D (50).

Late Policy

This course follows a strict project schedule, and as such, late assignments will not be accepted. Please plan your work accordingly to meet all deadlines.

Regrade Policy

If you believe there has been an error in the grading of your project artifacts, please submit a regrade request through Gradescope. We will carefully review your request, but please be aware that a regrade may result in your grade being adjusted either upward or downward. Regrade requests must be submitted within one week of the initial grade being posted.

Project

The project will be completed in groups of 2 to 3 students and consists of four key components: a proposal, a midpoint report, a final report, and a poster/oral presentation. This project is a central element of the course, designed to closely mirror the process of researching and writing a conference-style paper.

For detailed information about the project requirements, please see the project page.

Auditing

Audits are not permitted.

Use of AI

Students are welcome to use AI tools and other resources to support their research, prepare project reports, and develop presentations. However, they must ensure that all content is accurate, original, and free from plagiarism. Students are fully responsible for any misrepresentations, factual inaccuracies, or instances of plagiarism in their work. Additionally, students are expected to have a thorough understanding of all aspects of their projects and must be prepared to explain their work in detail during evaluations and presentations.

Past offerings of 670 at UMass

Related courses at UMass

Accommodation Statement

The University is committed to providing an equal educational opportunity for all students. If you have a documented physical, psychological, or learning disability on file with Disability Services (DS), you may be eligible for reasonable academic accommodations to help you succeed in this course. If you have a documented disability that requires an accommodation, please notify me within the first two weeks of the semester so that we may make appropriate arrangements.

Academic Honesty

Integrity is fundamental to the academic enterprise, and academic honesty is expected of all students. You are responsible for adhering to the standards of academic integrity outlined by the university. For more information, please refer to the UMass Academic Honesty Policy.

Acknowledgements

This version of 670 is inspried by courses offered by Gedas Bertasius, Stella Yu, and James Hays.