News

IEEE9mon
AstroMAE: Redshift Prediction Using a Masked Autoencoder with a Novel Fine-Tuning Architecture | IEEE Conference Publication | IEEE Xplore
To the best of our knowledge, AstroMAE represents the first application of a masked autoencoder to astronomical data. By ignoring labels during the pretraining phase, the encoder gathers a general ...
IEEE8mon
BiMAE - A Bimodal Masked Autoencoder Architecture for Single-Label Hyperspectral Image Classification
We employ Self-Supervised Learning and Masked Image Modeling techniques to tackle this task. Recognizing the challenges and costs associated with acquiring hyperspectral data, we aim to develop a ...
GitHub10mon
ZY-LIi/IEEE_TGRS_DEMAE
This is a slim implementation of the "DEMAE: Diffusion Enhanced Masked Autoencoder for Hyperspectral Image Classification With few Labeled Samples", which has been published at IEEE TGRS! And the ...
GitHub1y
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
@inproceedings{yan2023skeletonmae, title={SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training}, author={Yan, Hong and Liu, Yang and Wei, Yushen and Li, Guanbin and Lin, ...
Frontiers2y
Learning the heterogeneous representation of brain's structure from serial SEM images using a masked autoencoder - Frontiers
Keywords: neural segmentation, SEM image, masked autoencoder, image segmentation, self-supervised learning. Citation: Cheng A, Shi J, Wang L and Zhang R (2023) Learning the heterogeneous ...