GitHub

Diffusion Transformers with Representation Autoencoders (RAE)

We present Representation Autoencoders (RAE), a class of autoencoders that utilize pretrained, frozen representation encoders such as DINOv2 and SigLIP2 as encoders with trained ViT decoders. RAE can ...
IEEE

Masked Autoencoders for Ultrasound Signals: Robust Representation Learning for Downstream Applications

Abstract: We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ...
IEEE

Cutting-Edge Convolutional Neural Network Autoencoders for Anomaly Detection in ECG Signals: Advancements in Early Cardiac Diagnosis

Abstract: The current research deals with the complex domain of ECG signal processing and classification using convolutional neural network auto-encoders. Much attention was placed on the PTB ...
GitHub

Improved Baselines with Representation Autoencoders

RAEv2 simplifies and improves representation autoencoders, achieving over 10x faster convergence, better generation, and better reconstruction. RAEv2 achieves state-of-the-art gFID and FDr6 in just 80 ...