Firstly, the autoencoder model based on wavelet decomposition (WD ... and omni-dimensional dynamic convolution (ODConv), and used a fusion loss function to train the model. Experiment shows that the ...

A novel reduced deep convolutional neural network (RDCNN) embedded with stack autoencoder, that is, RDCSAE structure is introduced to extract the most discriminative unsupervised feature data by ...

This is an autoencoder with cylic loss and coding parsing loss for image compression and reconstruction. Network backbone is simple 3-layer fully conv (encoder) and symmetrical for decoder. Finally it ...