CyCNN：一种使用极坐标映射和柱面卷积层的旋转不变量CNN
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers
摘要：
深度卷积神经网络（CNN）在图像分类中经验上已知对适度平移不变，但对旋转不变。本文提出了一种深度CNN模型，称为CyCNN，它利用输入图像的极坐标映射将旋转转换为平移。为了处理极坐标的圆柱属性，我们将传统CNN中的卷积层替换为圆柱卷积（CyConv）层。CyConv层利用圆柱滑动窗口（CSW）机制，该机制垂直扩展卷积层中边界单元的输入图像感受野。我们评估了CyCNN和传统的CNN模型在旋转MNIST，CIFAR-10和SVHN数据集上的分类任务。我们表明，如果在训练过程中没有数据增强，与传统的CNN模型相比，CyCNN显着提高了分类精度。我们对CyCNN的实现可在https://github.com/mcrl/CyCNN上公开获得。
英文摘要：
Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification. This paper proposes a deep CNN model, called CyCNN, which exploits polar mapping of input images to convert rotation to translation. To deal with the cylindrical property of the polar coordinates, we replace convolution layers in conventional CNNs to cylindrical convolutional (CyConv) layers. A CyConv layer exploits the cylindrically sliding windows (CSW) mechanism that vertically extends the input-image receptive fields of boundary units in a convolutional layer. We evaluate CyCNN and conventional CNN models for classification tasks on rotated MNIST, CIFAR-10, and SVHN datasets. We show that if there is no data augmentation during training, CyCNN significantly improves classification accuracies when compared to conventional CNN models. Our implementation of CyCNN is publicly available on https://github.com/mcrl/CyCNN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
