← Search

Duncan Robertson

2 accepted papers

2017

Deep Roots: Improving CNN Efficiency With Hierarchical Filter Groups

CVPR 2017poster

We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost and number of parameters compared to state-of-the-art deep C…

Cited by 383PDFcodeScholar
2016

Refining Architectures of Deep Convolutional Neural Networks

CVPR 2016poster

Deep Convolutional Neural Networks (CNNs) have recently evinced immense success for various image recognition tasks. However, a question of paramount importance is somewhat unanswered in deep learning research - is the selected CNN optimal for the dataset in terms of accuracy and model size? In thi…

Cited by 40PDFScholar