Histology images are inherently symmetric under rotation, where each orientation is equally
as likely to appear. However, this rotational symmetry is not widely utilised as prior …

Group convolutional neural networks (G-CNNs) have been shown to increase parameter
efficiency and model accuracy by incorporating geometric inductive biases. In this work, we …

Deep neural networks can solve many kinds of learning problems, but only if a lot of data is
available. For many problems (eg in medical imaging), it is expensive to acquire a large …

We analyze the role of rotational equivariance in convolutional neural networks (CNNs)
applied to spherical images. We compare the performance of the group equivariant …

Despite recent advances in deep learning, the crucial task of nuclear segmentation for
computational pathology remains challenging. Recently, deep learning, and specifically U …

Recent improvements in generative adversarial visual synthesis incorporate real and fake
image transformation in a self-supervised setting, leading to increased stability and …

Thanks to their improved data efficiency, equivariant neural networks have gained increased
interest in the deep learning community. They have been successfully applied in the medical …

Robustness of deep learning segmentation models is crucial for their safe incorporation into
clinical practice. However, these models can falter when faced with distributional changes …

The morphological structure such as nuclei, glands, tumors, etc. of histopathological images
has been regularly analyzed by the pathologists in order to determine the extent of …

Incorporating either rotation equivariance or scale equivariance into CNNs has proved to be
effective in improving models' generalization performance. However, jointly integrating …