Graph neural networks (GNNs) are commonly described as being permutation equivariant
with respect to node relabeling in the graph. This symmetry of GNNs is often compared to …

Image keypoint descriptions that are discriminative and matchable over large changes in
viewpoint are vital for 3D reconstruction. However descriptions output by learned descriptors …

Any representation of data involves arbitrary investigator choices. Because those choices
are external to the data-generating process, each choice leads to an exact symmetry …

Contrastive learning has been a leading paradigm for self-supervised learning, but it is
widely observed that it comes at the price of sacrificing useful features (\eg colors) by being …

We propose a way to train deep learning based keypoint descriptors that makes them
approximately equivariant for locally affine transformations of the image plane. The main …

Group equivariant convolutional neural networks have been designed for a variety of
geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale …

We propose PseudoNeg-MAE, a novel self-supervised learning framework that enhances
global feature representation of point cloud mask autoencoder by making them both …

This work characterizes equivariant polynomial functions from tuples of tensor inputs to
tensor outputs. Loosely motivated by physics, we focus on equivariant functions with respect …

Text embedding has become a foundational technology in natural language processing
(NLP) during the deep learning era, driving advancements across a wide array of …

What do different contrastive learning (CL) losses actually optimize for? Although multiple
CL methods have demonstrated remarkable representation learning capabilities, the …