Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations

TL;DR

This paper analyzes the scale generalisation capabilities of Gaussian derivative networks on image datasets with spatial scaling variations, introducing extensions and demonstrating improved performance and explainability.

Contribution

The paper introduces conceptual and algorithmic extensions to Gaussian derivative networks, demonstrating enhanced scale generalisation and explainability on diverse image datasets.

Findings

GaussDerNets show strong scale generalisation on new datasets.

Average pooling over scales can outperform max pooling.

Scale-channel dropout improves performance and generalisation.

Abstract

This paper presents an in-depth analysis of the scale generalisation properties of the scale-covariant and scale-invariant Gaussian derivative networks, complemented with both conceptual and algorithmic extensions. For this purpose, Gaussian derivative networks (GaussDerNets) are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets, with spatial scaling variations over a factor of 4 in the testing data, that are not present in the training data. Additionally, evaluations on the previously existing STIR datasets show that the GaussDerNets achieve better scale generalisation than previously reported for these datasets for other types of deep networks. We first experimentally demonstrate that the GaussDerNets have quite good scale generalisation properties on the new datasets, and that average pooling of feature responses over scales may sometimes also lead to better results than the previously used approach of max pooling over scales. Then, we demonstrate that using a spatial max pooling mechanism after the final layer enables localisation of non-centred objects in image domain, with maintained scale generalisation properties. We also show that regularisation during training, by applying dropout across the scale channels, referred to as scale-channel dropout, improves both the performance and the scale generalisation. In additional ablation studies, we demonstrate that discretisations of GaussDerNets, based on the discrete analogue of the Gaussian kernel in combination with central difference operators, perform best or among the best, compared to a set of other discrete approximations of the Gaussian derivative kernels. Finally, by visualising the activation maps and the learned receptive fields, we demonstrate that the GaussDerNets have very good explainability properties.