IEEE

Soft Cluster-aware Equivariant Contrastive Learning for Unsupervised Out-of-Distribution Detection

Abstract: Recent works try to combine clustering and contrastive learning for unsupervised out-of-distribution (OOD) detection, since these two schemes can exploit semantic information and bring in ...
IEEE

On Equivariant and Invariant Learning of Object Landmark Representations

Abstract: Given a collection of images, humans are able to discover landmarks by modeling the shared geometric structure across instances. This idea of geometric equivariance has been widely used for ...
GitHub

odinhg/rotation-equivariant-contour-learning

This repository contains code for the paper RotaTouille: Rotation Equivariant Deep Learning for Contours. It implements rotation equivariant and invariant layers for deep learning on contour data. It ...
GitHub

Equivariant Splitting: Self-supervised learning from incomplete data

Abstract: Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based ...