Heterogeneous graph network convolutional masked autoencoder

Featured Image

Why is it important?

We propose a convolutional masked autoencoder (CMAE) to process the heterogeneous image after feature reconstruction. It mainly relies on the idea of sparse convolution in feature extraction. Only unmasked features are extracted. A feature cross-communication module is designed to establish communication between multiple modalities, so that the output features include all features of the modality as well as relevant information of other modalities.