Details

Autor(en) / Beteiligte

• Huang, Gao
• Liu, Shichen
• Maaten, Laurens van der
• Weinberger, Kilian Q.

Titel

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

Ist Teil von

• 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, p.2752-2761

Ort / Verlag

IEEE

Erscheinungsjahr

2018

Link zum Volltext

• IEEE_Xplore

Quelle

IEL

Beschreibungen/Notizen

• 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 ShuffleNets.