论文标题
流网络：通过硬连线和输入引起的稀疏性增加噪音鲁棒性和过滤多样性
Streaming Networks: Increase Noise Robustness and Filter Diversity via Hard-wired and Input-induced Sparsity
论文作者
论文摘要
CNN在许多应用程序中都取得了最先进的性能。最近的研究表明，如果图像破坏了噪声，CNN的识别精度会急剧下降。我们专注于噪声浪费图像的强大识别精度的问题。我们介绍了一种称为流网络的新型网络体系结构。每个流都将原始图像的一定强度切成片作为输入，并且流参数是独立训练的。我们使用网络容量，硬接线和输入诱导的稀疏度作为实验的维度。结果表明，只有硬连线和输入诱导稀疏性的存在才能实现强大的嘈杂图像识别。流网是唯一具有稀疏性且对噪声表现出更高鲁棒性的体系结构。最后，为了说明滤波器多样性的增加，我们说明了第一个交流层的滤波器重量的分布逐渐接近均匀分布，因为硬连线和域引起的稀疏性和能力的增加。
The CNNs have achieved a state-of-the-art performance in many applications. Recent studies illustrate that CNN's recognition accuracy drops drastically if images are noise corrupted. We focus on the problem of robust recognition accuracy of noise-corrupted images. We introduce a novel network architecture called Streaming Networks. Each stream is taking a certain intensity slice of the original image as an input, and stream parameters are trained independently. We use network capacity, hard-wired and input-induced sparsity as the dimensions for experiments. The results indicate that only the presence of both hard-wired and input-induces sparsity enables robust noisy image recognition. Streaming Nets is the only architecture which has both types of sparsity and exhibits higher robustness to noise. Finally, to illustrate increase in filter diversity we illustrate that a distribution of filter weights of the first conv layer gradually approaches uniform distribution as the degree of hard-wired and domain-induced sparsity and capacities increases.
