Conference Publication Details
Mandatory Fields
Peter Corcoran, Shabab Bazrafkan
Embedded Vision Summit 2018
Hybrid Semi-Parallel Deep Neural Networks (SPDNN) Example Methodologies & Use Cases
Optional Fields
Deep Learning Deep Neural Networks DNN Architecture DNN Methodology Biometrics
Jeff Bier
Santa Clara Convention Center, Santa Clara, California
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.
science foundation Ireland
Grant Details
13/SPP/12868 Next Generation Imaging for Smartphones & Embedded Imaging Devices
Publication Themes
Informatics, Physical and Computational Sciences