In this paper, we propose a multimodal transformer using parallel concatenated architecture. Instead of using patches, we use column stripes for images in R, G, B channels as the transformer input. The column stripes keep the spatial relations of original image. We incorporate the multimodal transformer with variational autoencoder for synthetic cross-modal data generation. The multimodal transformer is designed using multiple compression matrices, and it serves as encoders for Parallel Concatenated Variational AutoEncoders (PC-VAE). The PC-VAE consists of multiple encoders, one latent space, and two decoders. The encoders are based on random Gaussian matrices and don't need any training. We propose a new loss function based on the interaction information from partial information decomposition. The interaction information evaluates the input cross-modal information and decoder output. The PC-VAE are trained via minimizing the loss function. Experiments are performed to validate the proposed multimodal transformer for PC-VAE.
@article{arxiv.2210.16174,
title = {Multimodal Transformer for Parallel Concatenated Variational Autoencoders},
author = {Stephen D. Liang and Jerry M. Mendel},
journal= {arXiv preprint arXiv:2210.16174},
year = {2022}
}
Comments
NeurIPS 2022 Workshop on Vision Transformers: Theory and Application, New Orleans, LA, December 2022