I am a fourth-year PhD student in the CSE department at UCSD advised by Prof. Manmohan Chandrakar. My research interests span the areas of computer vision and machine learning. I am interested in learning representations of images and videos from limited labeled data that are useful and transferable across a wide range of domains. Specifically, I work on problems in domain adaptation, transfer learning, few shot learning and open world learning.

Previously, I worked as a research assistant at Centre for Visual Information and Technology (CVIT), IIIT Hyderabad on semantic segmentation on Indian roads. I did my bachelors from IIT Guwahati in 2016.

New large-scale dataset to study generalization properties of vision models across disparate geographies.

Memory-based consistency losses to scale unsupervised domain adaptation to a large number of classes, including fine-grained datasets.

Selected as finalist for Best Paper Award
(Top 12 out of 641 papers, Top 2%).

Fast, accurate and flow-free video frame interpolation technique using space-time convolutions, capable of single shot multi frame prediction.

Domain adaptation across datasets with disjoint labels using a deep-clustering based approach and an intermediate bridge domain.

Proposes multi sample contrastive loss using instance level similarities across source and target domains for robust feature alignment and knowledge transfer.

Addresses geographical disparities between semantic segmentation datasets with minimum labeling overhead from each domain.

Proposes optimum model and data resampling choices for resource constrained training of semantic segmentation networks.