ML Anthology

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger
CVPR 2018
doi:10.1109/CVPR.2018.00291 /cvpr/2018/huang2018cvpr-condensenet/

Abstract

Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a novel module called learned group convolution. The dense connectivity facilitates feature re-use in the network, whereas learned group convolutions remove connections between layers for which this feature re-use is superfluous. At test time, our model can be implemented using standard group convolutions, allowing for efficient computation in practice. Our experiments show that CondenseNets are far more efficient than state-of-the-art compact convolutional networks such as MobileNets and ShuffleNets.

PDF CVPR Semantic Scholar

Cite

Text

Huang et al. "CondenseNet: An Efficient DenseNet Using Learned Group Convolutions." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00291

Markdown

[Huang et al. "CondenseNet: An Efficient DenseNet Using Learned Group Convolutions." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/huang2018cvpr-condensenet/) doi:10.1109/CVPR.2018.00291

BibTeX

@inproceedings{huang2018cvpr-condensenet,
  title     = {{CondenseNet: An Efficient DenseNet Using Learned Group Convolutions}},
  author    = {Huang, Gao and Liu, Shichen and van der Maaten, Laurens and Weinberger, Kilian Q.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00291},
  url       = {https://mlanthology.org/cvpr/2018/huang2018cvpr-condensenet/}
}