TY - JOUR A2 - Zou, Liang AU - Ma, Ruixin AU - Lou, Junying PY - 2021 DA - 2021/04/02 TI - CPGAN :  An Efficient Architecture Designing for Text-to-Image Generative Adversarial Networks Based on Canonical Polyadic Decomposition SP - 5573751 VL - 2021 AB - Text-to-image synthesis is an important and challenging application of computer vision. Many interesting and meaningful text-to-image synthesis models have been put forward. However, most of the works pay attention to the quality of synthesis images, but rarely consider the size of these models. Large models contain many parameters and high delay, which makes it difficult to be deployed on mobile applications. To solve this problem, we propose an efficient architecture CPGAN for text-to-image generative adversarial networks (GAN) based on canonical polyadic decomposition (CPD). It is a general method to design the lightweight architecture of text-to-image GAN. To improve the stability of CPGAN, we introduce conditioning augmentation and the idea of autoencoder during the training process. Experimental results prove that our architecture CPGAN can maintain the quality of generated images and reduce at least 20% parameters and flops. SN - 1058-9244 UR - https://doi.org/10.1155/2021/5573751 DO - 10.1155/2021/5573751 JF - Scientific Programming PB - Hindawi KW - ER -