Rotation Invariance Neural Network

2017/06/17 by Shiyuan Li, Li, Shiyuan
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Image and Object Detection Techniques #Neural Networks and Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1706.05534

7 pages, 4 figures

arxiv created 2017/06/17 · openalex publication_date 2017/06/17 · arxiv updated 2017/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in 2-D symbol recognition. We can also get the position and orientation of the 2-D symbol by the network to achieve detection purpose for multiple non-overlap target. Last but not least, this architecture can achieve one-shot learning in some cases using those invariance.

Citations

• Gradient-based learning applied to document recognition
• ImageNet classification with deep convolutional neural networks
• One-shot Learning with Memory-Augmented Neural Networks

Related

• Rotation Equivariance and Invariance in Convolutional Neural Networks
• RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• Compensating for Large In-Plane Rotations in Natural Images
• RRL:Regional Rotation Layer in Convolutional Neural Networks