Unlike images which are represented in regular dense grids, 3D point clouds are irregular
and unordered, hence applying convolution on them can be difficult. In this paper, we extend …

In this paper we challenge the common assumption that convolutional layers in modern
CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial …

Convolutional neural networks (CNNs) are inherently limited to model geometric
transformations due to the fixed geometric structures in its building modules. In this work, we …

Translating or rotating an input image should not affect the results of many computer vision
tasks. Convolutional neural networks (CNNs) are already translation equivariant: input …

It has long been recognized that the invariance and equivariance properties of a
representation are critically important for success in many vision tasks. In this paper we …

In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of
a set of “basis filters.” Steerable properties dominate the design of the traditional filters, eg …

Abstract We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep
generative model for image sequences. It can reliably discover and track objects through the …

When designing Convolutional Neural Networks (CNNs), one must select the size\break of
the convolutional kernels before training. Recent works show CNNs benefit from different …

Although explainable artificial intelligence (XAI) promises considerable progress in
glassboxing deep learning models, there are challenges in applying XAI to geospatial …

Abstract Treatment selection is becoming increasingly more important in acute ischemic
stroke patient care. Clinical variables and radiological image biomarkers (old age, pre …