Log In Sign Up

Deep Rotation Equivariant Network

by   Junying Li, et al.

Recently, learning equivariant representations has attracted considerable research attention. Dieleman et al. introduce four operations which can be inserted to CNN to learn deep representations equivariant to rotation. However, feature maps should be copied and rotated four times in each layer in their approach, which causes much running time and memory overhead. In order to address this problem, we propose Deep Rotation Equivariant Network(DREN) consisting of cycle layers, isotonic layers and decycle layers.Our proposed layers apply rotation transformation on filters rather than feature maps, achieving a speed up of more than 2 times with even less memory overhead. We evaluate DRENs on Rotated MNIST and CIFAR-10 datasets and demonstrate that it can improve the performance of state-of-the-art architectures. Our codes are released on GitHub.


page 7

page 9


Inability of spatial transformations of CNN feature maps to support invariant recognition

A large number of deep learning architectures use spatial transformation...

SpecNet: Spectral Domain Convolutional Neural Network

The memory consumption of most Convolutional Neural Network (CNN) archit...

Unsupervised Learning of Neural Networks to Explain Neural Networks

This paper presents an unsupervised method to learn a neural network, na...

Rotated Feature Network for multi-orientation object detection

General detectors follow the pipeline that feature maps extracted from C...

Top-down Flow Transformer Networks

We study the deformation fields of feature maps across convolutional net...

Towards Efficient Convolutional Network Models with Filter Distribution Templates

Increasing number of filters in deeper layers when feature maps are decr...

Automated Multiscale 3D Feature Learning for Vessels Segmentation in Thorax CT Images

We address the vessel segmentation problem by building upon the multisca...

Code Repositories


DREN:Deep Rotation Equivirant Network

view repo


DREN Tensorflow rotate mnist

view repo