Project guidelines

Final projects will entail original investigation into any area of computer vision defined very broadly, or a focused literature review in a topic from such an area. That means that machine learning over visual data, HCI, computational photography, computer graphics, language-vision interfaces, computer vision applied to domains such as medical images, and so on, are all acceptable topics in addition to the core computer vision topics.

Scope

As a broad target, the final project should involve approximately as much work as two homework assignments for each student in the group. Thus, the total work should scale roughly linearly with the group size, and be distributed roughly equally. Similarly, multi-purpose projects which are being submitted for multiple classes should scale with the number of classes involved. An ambitious, well-done project from a group of two or more (or shared between two or more classes) should be on the order of a conference paper in depth of experimentation. I encourage you to tackle large problems in groups, for multiple classes, or both.

Milestones

  • Oct 23: Abstract due
  • December 5: Presentations
  • December 19: Final reports due

The abstract is just a short paragraph or two telling me who is in your group, describing the problem you've chosen, sketching the general approach you intend to take, and stating the kinds of data you're using. If you haven't already spoken to me about project ideas, you may want to stop by my office hours or to make an appointment before this point. The abstract mainly serves to give me a chance to make sure you're on a good path and to help me get a sense of who is doing what. Abstracts will have to be uploaded to Gradescope as a single pdf file. One submission per team is sufficient.

Towards the end of the class each team will make a short presentation or a poster describing their intermediate results. An important skill in research is to be able to tell in a week or two whether your ideas are basically going to work, well before you've fully done all engineering and experiments.

The final write-up should be on the order of 6-8 pages, describing your approach, results, data analysis, and so on. The initial abstract is a required checkpoint, but you will receive the bulk of the points at the end, based on your final write-ups. Take a look at the detailed rubric below.

Under normal circumstances, all group members will receive the same grade for the final project. Late days will not apply to the final reports. I have to get your grades in to the university, and I'm already giving you as long as I possibly can.

Grading (23% Total)

  • Abstract: 2%
  • Final report: 18%
    • write-up: 6%
      • clarity, structure, language, references: 2%
      • background literature survey, good understanding of the problem: 2%
      • good insights and discussions of methodology, analysis, results, etc.: 2%
    • technical: 7%
      • correctness: 3%
      • depth: 2%
      • innovation: 2%
    • evaluation and results: 5%
      • sound evaluation metric: 2%
      • thoroughness in analysis and experimentation: 2%
      • results and performance: 1%
  • Poster/Presentation: 3%

Ideas

You are welcome to come up with your own topics -- some of you already may have done so. Take a look at the the resources listed at the end of this page for potential topics. You are also welcome to come by my office hours to get ideas from me.

Literature review as an alternative: If you wish, you can instead write a literature review paper summarizing and comparing 3-5 papers on an advanced topic. If you are interested in this option, discuss this with me, I'll help you pick a good set of papers. Literature reviews are to be done solo.

Project resources

Some ideas:

  • Organizing personal photo collections. Think of all the photos you take on your mobile phone. What is a useful way of browsing and searching such a collection?
  • Better field-guides to categorize animals and plants using computer vision. Here is one for identifying tree species http://leafsnap.com.
  • Detecting interesting events in ego-centric cameras, e.g., GoPro. How can you tell when something interesting happens in the video stream?
  • Analyzing architecture – what cities are similar to Chicago in terms of the style of buildings?
  • Analyzing 3D dataset collections – how can you retrieve a 3D model from a computer graphics database using a photo? There are many 3D models available for download at https://3dwarehouse.sketchup.com. You might want to focus on a sub-category, say, airplanes.
  • List of computer vision datasets: http://www.cvpapers.com/datasets.html.
  • A list of project ideas from Serge Belongie at UCSD (→ Cornell Tech.) http://cseweb.ucsd.edu/classes/wi06/cse190a/projects.html
  • There are a number of computer vision startups with wide range of applications. These include sports replays, such as the “Goal-line” technology used this year in the FIFA world cup, medical applications, robotics, industrial inspections, etc. David Lowe maintains a (somewhat outdated) list of computer vision applications in the industry: http://www.cs.ubc.ca/~lowe/vision.html

A sample of projects from a prior course offering:

  • Scene text recognition
  • Improving object detection using depth estimation
  • Dust removal from images
  • Fast face-retrieval using vocabulary trees on deep features
  • Hyperspectral image classification
  • Character recognition in movies
  • Could motion analysis
  • Analysis of medical images
  • Stereo reconstruction survey
  • Counting heads in images
  • Implementation of a VR engine
  • Poselet based person identification
  • Gaze tracker
  • Photo stitching across seasons/day-night
  • Segmentation using CNNs
  • 3D Sketching
  • Survey (robotics + affordances)

Computing Resources

Some vision projects may involve large scale data and require GPU computing resources. We recommend you to check out "AWS Education" and "Google Cloud Platform".

  • AWS: https://aws.amazon.com/education/awseducate/
    • UMass is an "AWS member institution", so you are in the higher allowance tier. Use your .edu email and the full school name "University of Massachusetts Amherst" when you register to get the full benefits (a total of $100 annually).
    • To get GPUs, use g3 (up to 4 NVIDIA Tesla M60 GPUs) or p2 (up to 16 NVIDIA K80 GPUs) instances in EC2. Check the pricing first and make your plan accordingly!
  • Google Cloud Platform: https://cloud.google.com/
    • You get $300 credits for the first 12 months, and always free on their free-tier resources (not including GPUs)

Poster Session Guidelines

The poster session will be on Thursday, Dec 5, 10:30 AM-1 PM, in CS Building Room 150/151. Please arrive 10 minutes early to set everything up.

We recommend everyone to come, but it's OK to have only one person representing your team if you really cannot make it. Get in touch with the course staff to make alternate arrangements if no one from your team can be there.

Preparation

Your poster should be 24" x 36". It can be either horizontal or vertical. Also prepare for a short presentation of 2 minutes.

CSCF in our department provides one free poster printing per student per course. However, they only guarantee to print if you submit your file by the end of Monday 12/02 due to the large number of posters they need to handle. If you get your posters ready later than 12/02, contact CSCF directly to see if they have time to print it for you.

You can also print your poster elsewhere but you will need to pay for that. Options in town: Amherst Copy & Designworks, Staples, etc.

If you plan to paste several pieces of paper together as your poster (which is allowed but not recommended), please also let us know in advance, so that poster board paper will be provided as the background for your paste.

Guidelines to print posters in CSCF:

• Format: .pdf files - The file format of the files to be printed

• Size: recommend 24" x 36" - Poster dimensions, and if they were made on a Mac, Win, or Linux box

• Submission Instructions:

Log in to Secure Online Storage at UMass Amherst

- use your SPIRE NetID/password to login

- Click the “Upload" grey button in the upper right section of the window, choose pdf poster to upload to box

- The filename should be CourseNumber-NetID ( example: 670-Kellogg )

- Share the URL link to your file with cscf@umass.edu - Select your file and click the “Share” button

- Shared Link - Make sure “People with the link” is selected

- Email Shared Link - Type in cscf@umass.edu

- Click “Send"

Day of the event:

Foam board (24" x 36") and clips will be provided. We require using clips for affixing posters to foam board. Do not use tapes or thumbtacks on the boards. Foam boards and clips will be reused. Please do not break them, take them with you, or throw them away.