CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data
ETH Zurich, Zurich, Switzerland
arXiv:1704.04313 [cs.CV], (14 Apr 2017)
@article{cavigelli2017cbinfer,
title={CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data},
author={Cavigelli, Lukas and Degen, Philippe and Benini, Luca},
year={2017},
month={apr},
archivePrefix={"arXiv"},
primaryClass={cs.CV}
}
Extracting per-frame features using convolutional neural networks for real-time processing of video data is currently mainly performed on powerful GPU-accelerated workstations and compute clusters. However, there are many applications such as smart surveillance cameras that require or would benefit from on-site processing. To this end, we propose and evaluate a novel algorithm for change-based evaluation of CNNs for video data recorded with a static camera setting, exploiting the spatio-temporal sparsity of pixel changes. We achieve an average speed-up of 8.6x over a cuDNN baseline on a realistic benchmark with a negligible accuracy loss of less than 0.1% and no retraining of the network. The resulting energy efficiency is 10x higher than per-frame evaluation and reaches an equivalent of 328 GOp/s/W on the Tegra X1 platform.
April 17, 2017 by hgpu
