Density of Top-Layer Codes in Deep Convolutional Neural Networks Trained for Face Identification
Acknowledgements This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract No. 2014-14071600012. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Deep Convolutional Neural Networks (DCNNs) •Robust across image conditions (view, illumination, etc.) •Modeled after primate ventral visual stream [1,2]
Paper
Full text
Density of Top-Layer Codes in Deep Convolutional Neural Networks Trained for Face Identification
Semantic Scholar · Computer Science · 2019
Abstract
Acknowledgements This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract No. 2014-14071600012. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Deep Convolutional Neural Networks (DCNNs)
- Robust across image conditions (view, illumination, etc.)
- Modeled after primate ventral visual stream [1,2]