Computer Vision
Instructor: Subhransu Maji, Offering: Fall 2018
University of Massachusetts, Amherst
Instructor: Subhransu Maji, Offering: Fall 2018
University of Massachusetts, Amherst
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.
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.
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.
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.
Some ideas:
A sample of projects from a prior course offering:
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".
The poster session will be on Thursday, Dec 13, 10am-12pm, 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 Friday 12/7 due to the large number of posters they need to handle. If you get your poster ready later than 12/7, 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.