Om Khangaonkar

I'm a fourth-year undergrad (and soon-to-be PhD student) at UC Davis, advised by Hamed Pirsiavash. My research studies computer vision and machine learning.

Specifically, I am interested in the intersection of representation learning, generative modeling, and scene understanding. How can we learn to solve all perceptual tasks using as little labeled data as possible? How can we better understand how knowledge learned from large-scale visual data is structured? How can we use these insights to design better models of perception?

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.