Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network

06/18/2021
by   Sungwon Hwang, et al.
0

Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less dependence on data augmentation by achieving structural rotational invariance of a network. The deep equivariance-bridged SO(2) invariant network is proposed to echo such vision. First, Self-Weighted Nearest Neighbors Graph Convolutional Network (SWN-GCN) is proposed to implement Graph Convolutional Network (GCN) on the graph representation of an image to acquire rotationally equivariant representation, as GCN is more suitable for constructing deeper network than spectral graph convolution-based approaches. Then, invariant representation is eventually obtained with Global Average Pooling (GAP), a permutation-invariant operation suitable for aggregating high-dimensional representations, over the equivariant set of vertices retrieved from SWN-GCN. Our method achieves the state-of-the-art image classification performance on rotated MNIST and CIFAR-10 images, where the models are trained with a non-augmented dataset only. Quantitative validations over invariance of the representations also demonstrate strong invariance of deep representations of SWN-GCN over rotations.

READ FULL TEXT

page 1

page 5

research
09/11/2019

Geometric Graph Convolutional Neural Networks

Graph Convolutional Networks (GCNs) have recently become the primary cho...
research
05/12/2020

Benchmark Tests of Convolutional Neural Network and Graph Convolutional Network on HorovodRunner Enabled Spark Clusters

The freedom of fast iterations of distributed deep learning tasks is cru...
research
05/23/2023

Sorted Convolutional Network for Achieving Continuous Rotational Invariance

The topic of achieving rotational invariance in convolutional neural net...
research
05/14/2021

Multi-task Graph Convolutional Neural Network for Calcification Morphology and Distribution Analysis in Mammograms

The morphology and distribution of microcalcifications in a cluster are ...
research
02/05/2020

Structural Deep Clustering Network

Clustering is a fundamental task in data analysis. Recently, deep cluste...
research
11/14/2022

Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification

In recent years, research on hyperspectral image (HSI) classification ha...
research
09/03/2019

Embedding Symbolic Knowledge into Deep Networks

In this work, we aim to leverage prior symbolic knowledge to improve the...

Please sign up or login with your details

Forgot password? Click here to reset