Abstract: Autoencoders represent a significant category of deep learning models and are widely utilized for dimensionality reduction. However, standard Autoencoders are complicated architectures that ...

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 ...

MAESTRO_FLAIR-HUB_base — pre-trained on FLAIR-HUB MAESTRO_S2-NAIP-urban_base — pre-trained on S2-NAIP-urban Land cover segmentation in France, with 12 semantic classes. Note that the FLAIR#2 version ...

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) ...