LeanResNet: A Low-cost yet Effective Convolutional Residual Networks
LeanResNet: A Low-cost yet Effective Convolutional Residual Networks
复制标题
DOI：
--
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Jonathan Ephrath;Lars Ruthotto;E. Haber;Eran Treister
中科院分区：
文献类型：
--
作者：
Jonathan Ephrath;Lars Ruthotto;E. Haber;Eran Treister
卷积神经网络（CNNs）使用具有紧凑模板的空间卷积算子对输入数据进行过滤。通常，卷积算子会将所有通道的特征关联起来，这使得在CNN的训练和预测过程中计算成本极高。为提高CNN的效率，我们引入了精简卷积算子，该算子可减少参数数量和计算复杂度，并且可应用于现有的多种CNN。在此，我们以残差网络（ResNets）为例说明其应用，近年来残差网络一直非常可靠且得到了深入分析。在针对三个图像分类问题的实验中，我们提出的精简残差网络（LeanResNet）所取得的结果，与其他近期提出的、使用类似参数数量的精简架构相当。
Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introduce lean convolution operators that reduce the number of parameters and computational complexity, and can be used in a wide range of existing CNNs. Here, we exemplify their use in residual networks (ResNets), which have been very reliable for a few years now and analyzed intensively. In our experiments on three image classification problems, the proposed LeanResNet yields results that are comparable to other recently proposed reduced architectures using similar number of parameters.