Deep Rotating Kernel Convolution Neural Network

This paper describes a method that can be efficiently applied to data with rotational invariant characteristics such as texture. We propose a simple and highly scalable model that has excellent rotational invariant characteristics by using Rotating Kernel Convolution(RK Conv) which convolves and rotates kernel and Global Average Pooling (GAP) which invariant features to absolute position. The proposed model shows the state of the art performance in experiments under the same conditions as those in previous papers.

[1]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[2]  Li Liu,et al.  Rotation Invariant Local Binary Convolution Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[3]  Qiang Qiu,et al.  Oriented Response Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Patrick Follmann,et al.  A Rotationally-Invariant Convolution Module by Feature Map Back-Rotation , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).