17133

CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data

Lukas Cavigelli, Philippe Degen, Luca Benini
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}

}

Download Download (PDF)   View View   Source Source   

349

views

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.
VN:F [1.9.22_1171]
Rating: 4.2/5 (5 votes cast)
CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data, 4.2 out of 5 based on 5 ratings

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: