Adapted and Oversegmenting Graphs: Application to Geometric Deep Learning

TL;DR

This paper introduces an efficient iterative method to adapt graphs to image data, enabling salient feature detection and oversegmentation, which improves image analysis and classification performance.

Contribution

The paper presents a novel graph adaptation and oversegmenting approach that incorporates saliency measures, enhancing geometric deep learning applications.

Findings

Achieved over 90% boundary recall on synthetic and natural images.

Attained 97.86% accuracy on MNIST classification.

Method is computationally efficient and fully parallelisable.

Abstract

We propose a novel iterative method to adapt a a graph to d-dimensional image data. The method drives the nodes of the graph towards image features. The adaptation process naturally lends itself to a measure of feature saliency which can then be used to retain meaningful nodes and edges in the graph. From the adapted graph, we also propose the computation of a dual graph, which inherits the saliency measure from the adapted graph, and whose edges run along image features, hence producing an oversegmenting graph. The proposed method is computationally efficient and fully parallelisable. We propose two distance measures to find image saliency along graph edges, and evaluate the performance on synthetic images and on natural images from publicly available databases. In both cases, the most salient nodes of the graph achieve average boundary recall over 90%. We also apply our method to image classification on the MNIST hand-written digit dataset, using a recently proposed Deep Geometric Learning architecture, and achieving state-of-the-art classification accuracy, for a graph-based method, of 97.86%.