Equivariance wrt geometric transformations in neural networks improves data efficiency,
parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance …

The property of covariance, also referred to as equivariance, means that an image operator
is well-behaved under image transformations, in the sense that the result of applying the …

This paper develops an in-depth treatment concerning the problem of approximating the
Gaussian smoothing and the Gaussian derivative computations in scale-space theory for …

Convolutional neural networks benefit from translation equivariance achieving tremendous
success. Equivariant networks further extend this property to other transformation groups …

This paper presents an analysis of properties of two hybrid discretization methods for
Gaussian derivatives, based on convolutions with either the normalized sampled Gaussian …

The influence of natural image transformations on receptive field responses is crucial for
modelling visual operations in computer vision and biological vision. In this regard …

Medical images are often acquired in different settings, requiring harmonization to adapt to
the operating point of algorithms. Specifically, to standardize the physical spacing of imaging …

Scattering networks yield powerful and robust hierarchical image descriptors which do not
require lengthy training and which work well with very few training data. However, they rely …

In order to meet the growing demand for food and achieve food security development goals,
contemporary agriculture increasingly depends on plastic coverings such as agricultural …

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 …