review comment

[COMS W4731] Computer Vision

Departments: Computer Science

Professors: Shree Nayar

May 12, 2010

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

I can see why people like him, but the material is extremely difficult, beware!

He makes lectures interesting and funny, but he glosses over important concepts and you never feel like you understand anything until the difficult midterm and final come around. You'll have to study your ass off just to pass.

The programs are a lot fun. They take some thinking, but overall they're well-structured and very useful. The theory questions on homeworks are impossible.

What's very unfair about this course though is that you can't recover from a single bad grade on anything (hw, midterm, or final). A single mess-up will glare at you on your final grade, not to mention that the curve is very small. The difference between letter grades is very slight, only a few points will be bump you up from a B+ to an A (notice there's no A-). But only a few points will drop you down from a B+ to a B-.

Unfortunately he grades strictly by the numbers, and no amount of asking questions in class, going to office hours, or demonstrating grade improvement throughout the semester will factor into your final grade. He has no problem setting the average to a low grade.

Workload:

5 homeworks (they get easier over time)
1 midterm (impossible)
1 final (difficult)

April 15, 2008

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

Professor Shree Nayar is the best professor I met at Columbia. The course is very informative. He gives great lecture with a sense of humor. The TA are very helpful. The assignments are not that hard but yet gives you a sense of how things really work.

I highly recommend this course to anybody who has interest in vision/graphics. It's a must for students in vision/graphics track.

Highly recommended.

Workload:

Not bad. The assignments are getting easier after the third one. But you need to spend lots of time on the slides to make sure you really understands the materials.

Final and midterms are well organized.

March 03, 2008

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

Professor Nayar is tied for my favorite professor. The main reason I believe he is so good is because he conveys material in an extremely concise, understandable and well-spoken manner and really knows the subject inside-
out. He is also very approachable in person and makes an effort to know students on some basic level.

The only thing that was a little weird about the vision class was the lack of math -- it was all in the slides but there is essentially no math in the entire class, which is in sharp contrast to the textbook. In addition, the first homework is pretty ridiculous in many ways and shouldn't be considered as a measure of the class' overall worth.

Programming assignments are engaging, and exams are very fair. Prof. Nayar makes use of the entire spectrum of scores on exams, and I feel gives proper questions to let those who understand subjects thoroughly to stand out. The one complaint about them is that he does not even give a format for the exam, let alone sample questions -- this was very nerve-wracking for me personally but it ended up OK in the end.

Workload:

The workload for the class is VERY front-heavy, so just get down and dirty early to enjoy the freedom from work at the end of the semester. It can definitely be a more difficult workload, but not too bad.

January 15, 2008

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

Prof Nayar is a natural. He is clear and cogent and drives all the relevant points home. Be sure to hang on to every word he says, because its generally very deep. If possible, make notes on top of the slides he gives, they make it easier to understand them when you study for the exam. This is a no-nonsense course, only relevant stuff is taught. Therefore, read the slides very thoroughly. Its not much to read, compared to the Horn book which is quiet abstruse. The class is a great learning experience. Particularly because of the simplicity that Prof Nayar brings to it. If you ever have anything remotely close to Vision take this class. If you don't, take it to experience what a great teacher is like.

Workload:

5 assignments. If the first freaks you out, hang in there, things just get easier. Overall assignments are easy. The slide handouts are all you need to prepare for the exams, and yes, some presence of mind.

December 09, 2003

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

Please keep in mind that this review is more than 5 years old.

I loved this course. Professor Nayar is an excellent lecturer. He provides the class with handouts containing almost every slide he uses (yes, he uses slides on a projector, which is usually a bad sign, but he pulls it off well)... over 400 pages per student across the term. This minimizes how much you have to take down in terms of notes, and allows you to spend more of the lecture making sure you understand, rather than copying down diagrams.
I have to agree with the previous review: Professor Nayar's digressions are always interesting, and regardless of whether they help understand the material, they help understand the motivations, or how vision works in humans.
It's not an easy class, but if you come to lecture all the time and pay attention, you shouldn't have trouble with the homeworks...
the midterm and final may be a different matter though. However, the professor and TAs are very helpful in office hours.

Workload:

The homeworks aren't so bad... 5 or 6 of them, and I found that the programming actually got easier as the term went on (after the third homework). However, the midterm and final were... insane, I thought. The best study advice I can give is: If you think there's no way it'll be asked, memorize it.

November 23, 2003

Nayar, Shree Silver_nugget
[COMS W4731] Computer Vision

Please keep in mind that this review is more than 5 years old.

Excellent course taught by an excellent professor! The course revolves around the idea of teaching a computer to extract information from visual images, such as the position of an object, the position of edges, shape/depth of a scene from multiple images. Some of it will make you rethink the many things we as humans take for granted, and Shree likes to insert pertinent biological/philosophical/tech-biz tidbits that encourage an appreciation for the material beyond a purely CS perspective. The underlying theory could potentially get very mathematical, but Shree avoids that and focuses instead on the general ideas and principles. In sum, the subject material is interesting, challenging at times but rarely impossible. As a teacher, Shree is one of the best out there. He is entertaining, funny, and very dedicated to making sure we learn. He is also a very effective lecturer with excellent presentation. So, although he is quite a busy man (a lot of conferences to attend) and had the TAs teach a couple of classes, I feel that we learnt more in his classes than usual. All in all, a great experience and highly recommended.

Workload:

5 HW assignments, each of which involves both writting exercises and 3-5 programs. Programs can be challenging, but again there's nothing impossible. Shree and the TAs are very helpful. If you keep up with the class and don't procrastinate, you will be fine.

Directory Data

Dept/Subj Directory Course Professor Year Semester Time Section
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2010 Spring TR / 4:10- 5:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2008 Fall TR / 4:10- 5:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2006 Fall TR / 4:10- 5:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2005 Fall TR / 1:10- 2:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision John Kender 2004 Fall TR / 1:10- 2:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2003 Fall TR / 4:10- 5:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2002 Fall TR / 4:10- 5:25 PM 1
COMS / COMS COMS COMS W4731: Computer Vision Shree Nayar 2001 Fall TR / 4:10- 5:25 PM 1