January 28, 2020: Seminar by Dr. Anirban Chakraborty, Indian Institute of Science, Bangalore

Efficient utilization of data in designing computer vision solutions
by
Anirban Chakraborty
Department of Computational and Data Sciences 
Indian Institute of Science, Bangalore
 
Date: Tuesday, January 28, 2020
Time: 15:00-16:00 HRS
Venue: Seminar Room, 
            Electronics and Communication Sciences Unit 
            9th Floor, S. N. Bose Bhavan (Library Building)
 
 
Abstract
The performance of a deep neural net model depends heavily on the quantity and quality of data, using which it has been trained. Data is undoubtedly more precious than anything else in the era of deep learning and hence efficient utilization of data is of utmost importance. Under this theme, we shall discuss two computer vision tasks and our proposed solutions. First, we shall discuss the design of data efficient algorithms for the task of knowledge distillation as an application. In the second part, we would present a novel operator-in-the-loop person re-identification framework, highlighting the need for optimally utilizing all possible sources of information pertaining to the task.
 
Bio: Anirban Chakraborty is an Assistant Professor in the Department of Computational and Data Sciences, Indian Institute of Science, Bangalore. He received his Ph.D. in Electrical Engineering from the University of California, Riverside in 2014. Subsequently, he held research fellow positions with the National University of Singapore and Nanyang Technological University. After that, Anirban worked as a computer vision researcher at the Robert Bosch Research and Technology Centre, India before joining IISc in June 2017. His research interests lie in the broad areas of computer vision and machine learning.
 
All are cordially invited.
 
Dipti Prasad Mukherjee
Head, Electronics and Communication Sciences Unit