Om Khangaonkar

I'm a PhD student at UC Davis, advised by Hamed Pirsiavash. My research is supported in part by the GGCS Excellence Fellowship.

I also did my BS at UC Davis, where I recieved the CS Department Citation Award (top 10 in the department).

My research studies computer vision and machine learning.

Some of the questions that that motivate my research are:

• How can we learn to see and interact with the world using as little labeled data as possible?
• How can we better understand what large models understand about the visual world?
• How can we use these insights to design better models of perception and action?

I am very excited to collaborate, especially in areas related to computer vision. Send me an email if you want to chat!

We are hiring motivated students at UC Davis to work with us on challenging problems in computer vision and machine learning. Please fill out this form if interested.

Email  /  Twitter  /  Google Scholar

We finetune generative models (i.e. Stable Diffusion, MAE) to segment object instances for a narrow set of object types. We find many interesting properties emerge including 1) zero-shot generalization to objects nothing like finetuning data 2) excellent performance at segmenting fine structures 3) very precise object edges.

Thanks to Jon Barron for this website template.