Hybrid Semi-Parallel Deep Neural Networks (SPDNN) – Example Methodologies & Use Cases

Wednesday, May 23, 3:30 PM - 4:00 PM
Summit Track: 
Technical Insights II
Room 203/204

Deep neural networks (DNNs) are typically trained on specific datasets, optimized with particular discriminating capabilities. Often several different DNN topologies are developed solving closely related aspects of a computer vision problem. But to utilize these topologies together, leveraging their individual discriminating capabilities, requires implementing each DNN separately, increasing the cost of practical solutions.

In this talk, a methodology to merge multiple deep networks using graph contraction is developed. This provides a single network topology, achieving significant reduction in size over the individual networks. More significantly, this merged SPDNN network can be re-trained across the combined datasets used to train the original networks, improving its accuracy over the original networks. The result is a single network that is more generic, but with equivalent – or often enhanced – performance over a wider range of input data.

Examples of several problems in contemporary computer vision are solved using SPDNNs. These include significantly improving segmentation accuracy of eye-iris regions (a key component of iris biometric authentication) and mapping depth from monocular images, demonstrating equivalent performance to stereo depth mapping.


Peter Corcoran

University Professor & Science Foundation Ireland, Lead PI, Xperi

Peter Corcoran is a Fellow of IEEE, the Founding Editor of IEEE Consumer Electronics Magazine and holds a Personal Chair in Electronic Engineering at the College of Engineering & Informatics at National University of Ireland Galway (NUIG). He is a co-founder of FotoNation, now a core business unit of Xperi Inc., headquartered in San Jose. He is lead Principle Investigator and Director of C3Imaging, an Industry/Academic research partnership between Xperi corporation and the National University of Ireland Galway, partly funded by Science Foundation Ireland (SFI). His current research interests include biometrics, deep learning, embedded computer vision and consumer electronics. He is co-author on 300+ technical publications and co-inventor on c.300 granted US patents.

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