ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge
Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao
Abstract
Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images. Recently, transformer-based TIS models (such as DALL-E) have been proposed using the encoder-decoder architectures. Yet, these billion-scale TIS models are difficult to tune and deploy in resource-constrained environments. In addition, there is a lack of language-specific TIS benchmarks for Chinese, together with high-performing models with moderate sizes. In this work, we present ARTIST, A tRansformer-based Chinese Text-to-Image SynThesizer for high-resolution image generation. In ARTIST, the rich linguistic and relational knowledge facts are injected into the model to ensure better model performance without the usage of ultra-large models. We further establish a large-scale Chinese TIS benchmark with the re-production results of state-of-the-art transformer-based TIS models.Results show ARTIST outperforms previous approaches.
BibTeX
@inproceedings{liu-etal-2022-artist,
title = "{ARTIST}: A Transformer-based {C}hinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge",
author = "Liu, Tingting and
Wang, Chengyu and
Zhu, Xiangru and
Li, Lei and
Qiu, Minghui and
Huang, Jun and
Gao, Ming and
Xiao, Yanghua",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.62/",
doi = "10.18653/v1/2022.findings-emnlp.62",
pages = "881--888"
}