论文标题
CYCNN：使用极性映射和圆柱卷积层的旋转不变CNN
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers
论文作者
论文摘要
深度卷积神经网络（CNN）在经验上是中等翻译的不变性，而不是图像分类中的旋转。本文提出了一个名为Cycnn的深CNN模型，该模型利用了输入图像的极性映射以将旋转转换为翻译。为了处理极坐标的圆柱特性，我们将常规CNN中的卷积层替换为圆柱卷积（CYCONV）层。 CYCONV层利用了圆柱滑动窗口（CSW）机制，该机制垂直扩展了卷积层中边界单元的输入图像接收场。我们评估了旋转MNIST，CIFAR-10和SVHN数据集的CYCNN和常规CNN模型。我们表明，如果在训练过程中没有数据增加，则与常规的CNN模型相比，CYCNN可显着提高分类精度。我们的CYCNN实施可在https://github.com/mcrl/cycnn上公开获得。
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.
