no code implementations • 16 Sep 2021 • Mark Buckler, Neil Adit, Yuwei Hu, Zhiru Zhang, Adrian Sampson
Our key insights are that 1) pointwise convolutions commute with frequency transformation and thus can be computed in the frequency domain without modification, 2) each channel within a given layer has a different level of sensitivity to frequency domain pruning, and 3) each channel's sensitivity to frequency pruning is approximately monotonic with respect to frequency.
no code implementations • 16 Mar 2018 • Mark Buckler, Philip Bedoukian, Suren Jayasuriya, Adrian Sampson
Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices.
1 code implementation • ICCV 2017 • Mark Buckler, Suren Jayasuriya, Adrian Sampson
We propose a new image sensor design that can compensate for skipping these stages.