If you’ve read about unsupervised learning techniques before, you may have come across the term “autoencoder”. Autoencoders are one of the primary ways that unsupervised learning models are developed.

The repository gives an improved Transformer-ConvNet architecture with Masked AutoEncoder for Cardiac MRI Registration. The core of the Transformer is designed as a Masked AutoEncoder (MAE) and a ...

One potential approach to enhance model generalization is Masked Autoencoder Pretraining. This repository explores the feasibility of this approach to address the difficulties posed by varying working ...

Abstract: In this paper, a signal-guided masked autoencoder (S-MAE) based semi-supervised learning framework is proposed for high-precision positioning with limited labeled channel impulse response ...