Ashwin Vaswani

MSCV Graduate Student @ CMU | Previously @Google | B.E. CS @BITS Pilani

About

I am a Computer Vision graduate student at the Robotics Institute, Carnegie Mellon University (CMU). My interests lie in the fields of Machine Learning and Deep Learning and their applications in the domain of Computer Vision. I am now looking for full-time opportunities starting January 2024 around Computer Vision, Perception, Generative AI, and Machine Learning. 

I completed my undergraduate degree in Computer Science student from Birla Institute of Technology and Science (BITS Pilani), Goa Campus. My interests lie in the fields of Machine Learning and Deep Learning and their applications in the domain of Computer Vision. Previously, I worked as a pre-doctoral researcher at Google Research India where I was working in the MyHealth team on projects related to Assistive Healthcare to coach people to a healthy life using Computer Vision. Specifically, I worked on improving predictions with the help of hierarchical and multi-label information with a focus on making semantically better mistakes. Before that, I worked in the Data Science team at CommerceIQ to understand people's intent from their search language on retail platforms and to help brands grow on e-commerce by identifying digital shelves or market segments in which they are lagging. I have also worked as a research intern at Martinos Centre, Harvard Medical School, and MGH, where I worked on the problem of Universal Lesion Detection, Weakly supervised learning for Diabetic Retinopathy, Vessel Segmentation, and ROP classification in Retinal Imaging. I have also worked as a Research Intern at SHI Lab, University of Oregon working owww.ri.cmu.edu/n Video Understanding and Activity Recognition, and as an undergraduate researcher at Anuradha and Prashanth Palakurthi Centre for Artificial Intelligence Research (APPCAIR), BITS Goa where I worked on Knowledge Distillation.

In my previous experiences, I have worked on challenging problems such as Human Activity Recognition in sports, Static and Dynamic Gesture Recognition, Lesion detection in Medical Imagery, Recommendation Systems, etc. Apart from this, I also actively contribute to Open-source and am a core member of Society for Artificial Intelligence and Deep Learning (SAiDL) . I've also taught courses related to Deep Learning and Computer Vision to freshmen students and was a Teaching Assistant at the Neuromatch Academy.

Email-1 / Email-2 / CV / Github / LinkedIn / Projects / Blog

Google Scholar / Research Gate

News