The first two classes will introduce you to active research topics in learning with limited labels for computer vision. This includes unsupervised learning with generative models, self-supervised learning, transfer learning, domain adaptation, and few-shot learning.  The goal is to provide a sufficient overview of problems in learning with limited labels for computer vision to enable an informed decision regarding the course project topic. You will work on the project through the semester as part of a team of 3-4 students (depending on enrollment).

After the introductory classes, you will read and review a paper (listed in the schedule) prior to each class. Each lecture will start with a  discussion of the paper that was reviewed. The discussion will be led by two students -- one highlighting the strengths of the paper, and the other highlighting the weaknesses.

Following the paper discussion, 3 teams will present their project ideas, updates and the issues they faced for about 10 min. each. The goal is to have enough time for discussion and brainstorming. On average, each team will present updates on their project ~3 times over the course of the semester. At the end of the semester, teams will give final project presentations.

Feedback is very welcome. If you have any questions or concerns about the class or the requirements, please be sure to discuss them with the instructor early on.

No laptops, cell phones or other distractions in class please.

Summary:

• 22 paper reviews (lowest 7 dropped)

• 1 paper discussion lead

• 2 project presentations (idea proposal and final presentation)

• 1 project update check-in

• 1 project spotlight video

NOTE: There will be no final exam!

Auditing the class: Students are required to submit reviews for 4 papers on the topics of unsupervised learning (Goodfellow et al, NeurIPS 2015), self-supervised learning (Pathak et al, CVPR 2017), transfer learning (Ganin et al, JMLR 2015), and few-shot learning (Snell et al, NeurIPS 2017). Students should attend all lectures and participate in discussions. Students need not lead discussions or do a project.

Pass/Fail - Students are required to submit reviews for 7 papers of their choice from the list of papers in the schedule. Students should attend all lectures and participate in discussions. Students need not lead discussions or do a project.

All students must follow the academic integrity and Georgia Tech Honor Code.