论文标题
稀疏和缩小网络以增加扭曲的鲁棒性
Sparsifying and Down-scaling Networks to Increase Robustness to Distortions
论文作者
论文摘要
已经表明，训练有素的网络在出现扭曲的图像时表现出大幅度降低性能。流媒体网络（STNET）是一种新型的架构，可以在未经发生的图像上训练时对扭曲的图像进行稳健分类。通过稀疏输入和隔离平行流具有脱钩的权重，可以实现失真鲁棒性。最近的结果证明，STNET对20种噪声和扭曲是强大的。 STNET表现出用于弱光图像分类的最新性能，而在其他网络时的尺寸要小得多。在本文中，我们使用缩放版本（每一层中的过滤器数量减少了n倍的n元素），例如VGG16，Resnet50和Mobilenetv2作为并行流的流行网络。这些新的Stnet在几个数据集上进行了测试。我们的结果表明，与原始网络相比，新的STNET效率更高（较少的失败）表现出更高或平等的精度。考虑到用于测试的各种数据集和网络，我们得出结论，一种新型的STNET是一种有效的扭曲图像分类的工具。
It has been shown that perfectly trained networks exhibit drastic reduction in performance when presented with distorted images. Streaming Network (STNet) is a novel architecture capable of robust classification of the distorted images while been trained on undistorted images. The distortion robustness is enabled by means of sparse input and isolated parallel streams with decoupled weights. Recent results prove STNet is robust to 20 types of noise and distortions. STNet exhibits state-of-the-art performance for classification of low light images, while being of much smaller size when other networks. In this paper, we construct STNets by using scaled versions (number of filters in each layer is reduced by factor of n) of popular networks like VGG16, ResNet50 and MobileNetV2 as parallel streams. These new STNets are tested on several datasets. Our results indicate that more efficient (less FLOPS), new STNets exhibit higher or equal accuracy in comparison with original networks. Considering a diversity of datasets and networks used for tests, we conclude that a new type of STNets is an efficient tool for robust classification of distorted images.
