CS 280 Graduate CV
Published:
Archive
Notes and Cheat Sheet
Review
A long-awaited sequel to CS 180 from the Fall, CS 280 solidified my CV fundamentals and dove headfirst into research topics. The first half of the class was essentially a beefed up version of 180. The Jitendra Malik came in and gave 2 pretty insightful lectures about the invention of homogeneous coordinates. Then we covered SfM and neural/transformers based methods. The coverage of flow matching and diffusion were much more rigorous than 180; Prof. Kanazawa taught it based on the ODE and SDE viewpoint rather than invertible networks (thank goodness). As always, it’s great to hear Efros lecture. This time around he hit us with some hard-hitting and timely questions about self supervised learning. The last unit, we covered Dust3r, VGGT, World Models, pose estimation, 4D, and a lot more researchy topics.
Supposedly Alyosha’s eyes are in poor shape so he compensated by becoming a computer vision researcher, which I found endearing.
CS 280 was a fun class, as in 5/5 in fun and 3.5/5 in difficulty. I nearly topped the semester-end exam (Gradescope put me in the highest bin in a class of mostly EECS PhDs!), but didn’t fare too well in the final paper. After great initial results, my partner and I put off the project for a bit too long and didn’t get to run some important ablations.
