Compared to the previously introduced variational autoencoder for natural text where both the encoder and decoder are RNN-based, we propose a new transformer-based architecture and augment the decoder ...

Abstract: A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders [1], as ...

Due to the limited receptive field of convolution kernels, fusion methods based on convolutional ... proposed multiscale spatial–spectral Transformer network. The architecture diagram of the masked ...

In this work, we propose TRACE, a Transformer-based recurrent VAE structure. TRACE imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the ...