no code implementations • 6 Sep 2023 • Priyam Mazumdar, Aiman Soliman, Volodymyr Kindratenko, Luigi Marini, Kenton McHenry
The proposed architecture is the Masked Autoencoder pre-trained on ImageNet (with the limitation that there is a large domain discrepancy between ImageNet and DEM) with an UperNet Head for decoding segmentations.