Idioma:

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

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

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

Texto completo disponível

Citações Citado por

Título:
CondenseNet: An Efficient DenseNet Using Learned Group Convolutions
Autor: Huang, Gao ; Liu, Shichen ; Maaten, Laurens van der ; Weinberger, Kilian Q.
Assuntos: Computational modeling ; Computer architecture ; Indexes ; Mobile handsets ; Network architecture ; Training
É parte de: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, p.2752-2761
Descrição: 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.
Editor: IEEE
Idioma: Inglês

Voltar para lista de resultados