Improving Text-to-Image Synthesis Using Contrastive Learning

By Hui Ye, Xiulong Yang, Martin Takác, Rajshekhar Sunderraman, Shihao Ji. 2021

93 citations recorded by the source corpus.

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of words. The linguistic discrepancy between the captions of the identical image leads to the synthetic images deviating from the ground truth. To address this issue, we propose a contrastive learning approach to improve the quality and enhance the semantic consistency of synthetic images. In the pretraining stage, we utilize the contrastive learning approach to learn the consistent textual representations for the captions corresponding to the same image. Furthermore, in the following stage of GAN training, we employ the contrastive learning method to enhance the consistency between the generated images from the captions related to the same image. We evaluate our approach over two popular text-to-image synthesis models, AttnGAN and DM-GAN, on datasets CUB and COCO, respectively. Experimental results have shown that our approach can effectively improve the quality of synthetic images in terms of three metrics: IS, FID and R-precision. Especially, on the challenging COCO dataset, our approach boosts the FID signifcantly by 29.60% over AttnGAN and by 21.96% over DM-GAN.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (2022, methodology): “42 - - - - DM-GAN+CL [65]”
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (2021, neutral): “(Zhu et al., 2019) 32.64 DF-GAN (Tao et al., 2020) 21.42 DM-GAN + CL (Ye et al., 2021) 20.79 XMC-GAN (Zhang et al., 2021) 9.33 LAFITE (Zhou et al., 2021) 8.12 DALL-E (Ramesh et al., 2021) ∼ 28 LAFITE (Zhou et al., 2021) 26.94 GLIDE 12.24 GLIDE (Validation ﬁltered)”
Towards Language-Free Training for Text-to-Image Generation (2021, methodology): “We consider a suite of datasets that are commonly used in literature [53, 54, 56, 59], including MSCOCO [4], CUB [47], LN-COCO [36], Multi-modal CelebA-HQ (MM CelebA-HQ) [52].”
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022, background): “[78] Hui Ye, Xiulong Yang, Martin Takac, Rajshekhar Sunderraman, and Shihao Ji.”
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models (2023, background): “Early works studied text-guided image synthesis in the context of GANs [Tao et al. 2022; Xu et al. 2018; Ye et al. 2021; Zhang et al. 2021; Zhu et al. 2019].”
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion (2022, background): “, 2018) or cross-modal contrastive approaches (Zhang et al., 2021; Ye et al., 2021).”