Title Of the Talk: Improving machine vision using insights from biological vision
Speaker: Dr S P Arun
Host Faculty: Dr. Vineeth N Balasubramanian
Date & Time: Monday, 19th April 2:45pm
Seminar link: https://us02web.zoom.us/j/89335972396?pwd=Sk15MFZSM3o5Qy80MElxMHJsSmEvUT09
Abstract:
Deep neural networks have revolutionized computer vision with their impressive performance on vision tasks. Recently their object representations have been found to match well to the visual areas of the brain. Yet their performance is still far worse than humans, and it has been challenging to derive insight into why deep networks work or how they can be improved. In our lab, we have been comparing object representations in brains and deep networks with the aim of understanding how we see. We have shown that systematic biases in deep networks can be identified by comparing with brain representations, and that fixing these biases can improve performance. We have also been testing deep networks for the presence/absence of a variety of classic perceptual phenomena. Taken together, these results suggest that accumulated wisdom from vision neuroscience might help to understand and improve deep neural networks.
Dr S P Arun received his B.Tech from IIT Bombay, and MS & PhD from Johns Hopkins University, all in Electrical Engineering. He completed his postdoctoral research at Carnegie Mellon University and joined the Centre for Neuroscience at IISc where he is currently an Associate Professor. He is fascinated by how the brain transforms sensations into perception. For more details visit the homepage of his research group, the Vision Lab @ IISc.
https://sites.google.com/site/visionlabiisc/.
Speaker Profile:
Dr. Somak Aditya (Microsoft Research India, Personal Webpage ) is currently a Postdoctoral Researcher at Microsoft Research India. He was awarded his Ph.D. for the dissertation “Knowledge and Reasoning for Image Understanding'' from Arizona State University in 2018. He has a background in NLP, Knowledge Representation and Reasoning, and Machine Learning; and is experienced in conducting interdisciplinary research in the field of AI. After demonstrating the need for knowledge and reasoning in vision and language applications, he has explored the same in the Marketing domain during his 1.5 years stint at Adobe Research, and then broadly in Natural Language Processing at Microsoft Research. Through workshops, Somak Aditya has actively promoted knowledge integration in the community. He has been a co-organizer for 3 workshops: the R2K workshop in KR 2018 in Phoenix, Arizona, the NSNLI workshop in IJCAI 2021, and the KINN workshop in CIKM 2021.
Dates:
Monday, 19th April 2:45pm