论文标题
深度多种卷积，用于降低网络参数而不牺牲准确性
Depthwise Multiception Convolution for Reducing Network Parameters without Sacrificing Accuracy
论文作者
论文摘要
近年来，深度卷积神经网络已被证明在多个基准挑战中获得了成功。但是，性能的改进在很大程度上依赖于日益复杂的网络架构和大量参数，这需要越来越多的存储和内存容量。深度可分离卷积（DSCONV）可以通过将标准卷积分解为空间和跨渠道卷积步骤，有效地减少所需参数的数量。但是，该方法导致准确性降解。为了解决这个问题，我们提出了深度的多音素卷积，称为多重接收，它引入了层的多尺寸内核，以同时学习所有单个输入通道的多尺度表示。我们使用五个流行的CNN模型，在所有模型中均获得了精确促进，并且与相关工作相比，使用五种流行的CNN模型，我们已经对四个基准数据集进行了实验，即CIFAR-10，CIFAR-100，STL-10和IMAGENET32X32。同时，多种次数将基于标准卷积模型的参数的数量显着减少了32.48％，同时仍保持准确性。
Deep convolutional neural networks have been proven successful in multiple benchmark challenges in recent years. However, the performance improvements are heavily reliant on increasingly complex network architecture and a high number of parameters, which require ever increasing amounts of storage and memory capacity. Depthwise separable convolution (DSConv) can effectively reduce the number of required parameters through decoupling standard convolution into spatial and cross-channel convolution steps. However, the method causes a degradation of accuracy. To address this problem, we present depthwise multiception convolution, termed Multiception, which introduces layer-wise multiscale kernels to learn multiscale representations of all individual input channels simultaneously. We have carried out the experiment on four benchmark datasets, i.e. Cifar-10, Cifar-100, STL-10 and ImageNet32x32, using five popular CNN models, Multiception achieved accuracy promotion in all models and demonstrated higher accuracy performance compared to related works. Meanwhile, Multiception significantly reduces the number of parameters of standard convolution-based models by 32.48% on average while still preserving accuracy.
