Tan, Zhaorui, Yang, Xi, Ye, Zihan, Wang, Qiufeng, Yan, Yuyao, Nguyen, Anh ORCID: 0000-0002-1449-211X and Huang, Kaizhu
(2023)
Semantic Similarity Distance: Towards better text-image consistency metric in text-to-image generation.
Pattern Recognition, 144.
p. 109883.
Text
2210.15235 (1).pdf - Author Accepted Manuscript Access to this file is embargoed until 14 August 2024. Download (20MB) |
Abstract
Generating high-quality images from text remains a challenge in visual-language understanding, with text-image consistency being a major concern. Particularly, the most popular metric R-precision may not accurately reflect the text-image consistency, leading to misleading semantics in generated images. Albeit its significance, designing a better text-image consistency metric surprisingly remains under-explored in the community. In this paper, we make a further step forward to develop a novel CLIP-based metric, Semantic Similarity Distance (SSD), which is both theoretically founded from a distributional viewpoint and empirically verified on benchmark datasets. We also introduce Parallel Deep Fusion Generative Adversarial Networks (PDF-GAN), which use two novel components to mitigate inconsistent semantics and bridge the text-image semantic gap. A series of experiments indicate that, under the guidance of SSD, our developed PDF-GAN can induce remarkable enhancements in the consistency between texts and images while preserving acceptable image quality over the CUB and COCO datasets.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Text-to-image, Image generation, Generative adversarial networks, Semantic consistency |
Divisions: | Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science |
Depositing User: | Symplectic Admin |
Date Deposited: | 04 Sep 2023 08:56 |
Last Modified: | 18 Oct 2023 18:11 |
DOI: | 10.1016/j.patcog.2023.109883 |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3172512 |