Translational equivariance, one of the properties of Convolutional neural networks (CNNs),
directly reflects the coherence of the influence of input at each position on the output. By …

The convolutional layers of standard convolutional neural networks (CNNs) are equivariant
to translation. However, the convolution and fully-connected layers are not equivariant or …

Abstract Convolutional Neural Networks (CNNs) are becoming increasingly popular in
autonomous driving. Researchers are focused on optimizing these models to work on …

Equivariance guarantees that a model's predictions capture key symmetries in data. When
an image is translated or rotated, an equivariant model's representation of that image will …

Deep Learning (DL) methods extract complex set of features using architectures containing
hierarchical set of layers. The features so learned have high discriminative power and thus …

Models can be compared against each other. Such comparison helps to find strengths and
weaknesses of different approaches and gives additional possibilities for model validation …

Aside from developing methods to embed the equivariant priors into the architectures, one
can also study how the networks learn equivariant properties. In this work, we conduct a …

Performance of neural networks can be significantly improved by encoding known
invariance for particular tasks. Many image classification tasks, such as those related to …

The popular convolutional neural networks (CNN) require data augmentation to achieve
rotation invariance. We propose an alternative mechanism, Pre-Rotation Only at Inference …

Neural networks are currently the state-of-the-art for many tasks.. Invariance and
sameequivariance are two fundamental properties to characterize how a model reacts to …