CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers

Abstract

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.

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Group Equivariant Convolutional Networks
• Billion-scale semi-supervised learning for image classification
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• Learning Invariant Representations with Local Transformations

Cited by in corpus (6)

• Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks
• Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
• Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
• Cosmic topology. Part IVa. Classification of manifolds using machine learning: a case study with small toroidal universes
• Automatic Analysis System of Calcaneus Radiograph: Rotation-Invariant Landmark Detection for Calcaneal Angle Measurement, Fracture Identification and Fracture Region Segmentation
• Circular-Symmetric Correlation Layer based on FFT