论文标题
轻量级残留密度连接的卷积神经网络
Lightweight Residual Densely Connected Convolutional Neural Network
论文作者
论文摘要
极其有效的卷积神经网络体系结构是有限资源设备（例如嵌入式和移动设备）的最重要要求之一。计算能力和内存大小是这些设备的两个重要约束。最近，已经提出了一些架构来通过考虑特定的硬件软件设备来克服这些限制。在本文中，提出了轻巧的残留密集连接块，以确保深入监督，有效的梯度流以及卷积神经网络的重复使用能力。所提出的方法通过减少参数和计算操作的数量，同时达到可行的精度，从而降低了训练和推理过程的成本，而无需使用任何特殊的软件设备。广泛的实验结果表明，就模型大小，所需参数甚至准确性而言，所提出的架构比Alexnet和VGGNet更有效。提出的模型已在Imagenet，Mnist，Fashion Mnist，SVHN，CIFAR-10和CIFAR-100上进行了评估。它在时尚MNIST数据集上取得了最新的结果，并为其他数据集取得了合理的结果。获得的结果表明，所提出的方法对有效模型（例如挤压）的优越性。它也可以与最先进的有效模型（例如冷凝网和沙夫列网）相媲美。
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints of these devices. Recently, some architectures have been proposed to overcome these limitations by considering specific hardware-software equipment. In this paper, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed method decreases the cost of training and inference processes without using any special hardware-software equipment by just reducing the number of parameters and computational operations while achieving a feasible accuracy. Extensive experimental results demonstrate that the proposed architecture is more efficient than the AlexNet and VGGNet in terms of model size, required parameters, and even accuracy. The proposed model has been evaluated on the ImageNet, MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. It achieves state-of-the-art results on Fashion MNIST dataset and reasonable results on the others. The obtained results show the superiority of the proposed method to efficient models such as the SqueezNet. It is also comparable with state-of-the-art efficient models such as CondenseNet and ShuffleNet.
