Constraint-Aware Deep Neural Network Compression

Abstract

Deep neural network compression has the potential to bring modern resource-hungry deep networks to resource-limited devices. However, in many of the most compelling deployment scenarios of compressed deep networks, the operational constraints matter: for example, a pedestrian detection network on a self-driving car may have to satisfy a latency constraint for safe operation. We propose the first principled treatment of deep network compression under operational constraints. We formulate the compression learning problem from the perspective of constrained Bayesian optimization, and introduce a cooling (annealing) strategy to guide the network compression towards the target constraints. Experiments on ImageNet demonstrate the value of modelling constraints directly in network compression.

Cite

Text

Chen et al. "Constraint-Aware Deep Neural Network Compression." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01237-3_25

Markdown

[Chen et al. "Constraint-Aware Deep Neural Network Compression." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/chen2018eccv-constraintaware/) doi:10.1007/978-3-030-01237-3_25

BibTeX

@inproceedings{chen2018eccv-constraintaware,
  title     = {{Constraint-Aware Deep Neural Network Compression}},
  author    = {Chen, Changan and Tung, Frederick and Vedula, Naveen and Mori, Greg},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01237-3_25},
  url       = {https://mlanthology.org/eccv/2018/chen2018eccv-constraintaware/}
}