Signature-Graph Networks

Abstract

We propose a novel approach for visual representation learning called Signature-Graph Neural Networks (SGN). SGN learns latent global structures that augment the feature representation of Convolutional Neural Networks (CNN). SGN constructs unique undirected graphs for each image based on the CNN feature maps. The feature maps are partitioned into a set of equal and non-overlapping patches. The graph nodes are located on high-contrast sharp convolution features with the local maxima or minima in these patches. The node embeddings are aggregated through novel Signature-Graphs based on horizontal and vertical edge connections. The representation vectors are then computed based on the spectral Laplacian eigenvalues of the graphs. SGN outperforms existing methods of recent graph convolutional networks, generative adversarial networks, and auto-encoders with image classification accuracy of 99.65% on ASIRRA, 99.91% on MNIST, 98.55% on Fashion-MNIST, 96.18% on CIFAR-10, 84.71% on CIFAR-100, 94.36% on STL10, and 95.86% on SVHN datasets. We also introduce a novel implementation of the state-of-the-art multi-head attention (MHA) on top of the proposed SGN. Adding SGN to MHA improved the image classification accuracy from 86.92% to 94.36% on the STL10 dataset

References in corpus (21)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Wide Residual Networks
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Adversarially Learned Inference
• Large-Scale Evolution of Image Classifiers
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Deep Anomaly Detection with Outlier Exposure
• Deep Variational Information Bottleneck
• SpinalNet: Deep Neural Network with Gradual Input
• Training Neural Networks with Local Error Signals
• APAC: Augmented PAttern Classification with Neural Networks
• ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
• Extended Batch Normalization
• DartsReNet: Exploring new RNN cells in ReNet architectures
• flexgrid2vec: Learning Efficient Visual Representations Vectors
• Rethinking Recurrent Neural Networks and Other Improvements for Image Classification