
Sujoy Paul
I am a Research Scientist at Google working on the intersection of computer vision and machine learning, with specific interests in self-supervised learning, semantic segmentation, domain adaptation, image generation, video and scene analysis. My interests also include reinforcement learning for robotics, along with imitation learning and policy adaptation. Prior to joining Google, I did my PhD from University of California, Riverside on learning from limited supervision for static and dynamic tasks in computer vision and robotics.
Research Areas
Authored Publications
Sort By
Google
Test-time Adaptation with Slot-centric Models
Mihir Prabhudesai
Anirudh Goyal
Gaurav Aggarwal
Thomas Kipf
Deepak Pathak
Katerina Fragkiadaki
International Conference on Machine Learning (2023), pp. 28151-28166
Novel Class Discovery without Forgetting
Joseph K J
Gaurav Aggarwal
Soma Biswas
Piyush Rai
Kai Han
Vineeth N Balasubramanian
European Conference on Computer Vision (ECCV) (2022)
Spacing Loss for Discovering Novel Categories
Joseph K J
Gaurav Aggarwal
Soma Biswas
Piyush Rai
Kai Han
Vineeth N Balasubramanian
Computer Vision and Pattern Recognition (CVPR) Workshop on Continual Learning in Computer Vision (2022)
What can we do with just the model? A simple knowledge extraction framework
Ansh Khurana
Gaurav Aggarwal
International Conference on Machine Learning. Principles of Distribution Shift Workshop (2022) (to appear)
Cross-domain Imitation from Observations
Dripta S Raychaudhuri
Jeroen van Baar
Amit K Roy-Chowdhury
International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research (PMLR) (2021)