Separable Convolutions for Efficient Implementation of CNNs and Other Vision Algorithms

Summit Track: 
Fundamentals

Separable convolutions are an important technique for implementing efficient convolutional neural networks (CNNs), made popular by MobileNet’s use of depthwise separable convolutions. But separable convolutions are not a new concept, and their utility is not limited to CNNs. Separable convolutions have been widely studied and employed in classical computer vision algorithms as well, in order to reduce computation demands. We begin this talk with an introduction to separable convolutions. We then explore examples of their application in classical computer vision algorithms and in efficient CNNs, comparing some recent neural network models. We also examine practical considerations of when and how to best utilize separable convolutions in order to maximize their benefits.

Speaker(s):

Chen-Ping Yu

Co-founder and CEO, Phiar

Dr. Chen-Ping Yu is the co-founder and CEO of Phiar, a company building the first AI-powered augmented reality smartphone navigation solution for driving. He was previously a postdoctoral fellow at Harvard University, researching neuro-inspired deep learning. Chen-Ping received his Ph.D. from Stony Brook University in Computer Vision and Machine Learning, and his M.S. from Penn State University. Chen-Ping has been an NSF Fellow and the recipient of numerous honors and awards, and has published more than 15 scientific publications at top AI and cognitive science venues.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!