# Text-to-image Synthesis via Symmetrical Distillation Networks

arXiv: https://arxiv.org/abs/1808.06801 · HTML: https://mlsanity.com/paper/1808.06801/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2018.

## Built on by (most cited first, 7 of 7)

- [Grid Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2404.00234/) (2024)
- [ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design](https://mlsanity.com/paper/2208.05621/) (2022)
- [DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment](https://mlsanity.com/paper/2308.11206/) (2023)
- [Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation](https://mlsanity.com/paper/2210.04468/) (2022)
- [DR-GAN: Distribution Regularization for Text-to-Image Generation](https://mlsanity.com/paper/2204.07945/) (2022)
- [DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs](https://mlsanity.com/paper/2108.01216/) (2021)
- [Text-To-Image with Generative Adversarial Networks](https://mlsanity.com/paper/2410.08608/) (2024)

## Abstract (arXiv)

Text-to-image synthesis aims to automatically generate images according to text descriptions given by users, which is a highly challenging task. The main issues of text-to-image synthesis lie in two gaps: the heterogeneous and homogeneous gaps. The heterogeneous gap is between the high-level concepts of text descriptions and the pixel-level contents of images, while the homogeneous gap exists between synthetic image distributions and real image distributions. For addressing these problems, we exploit the excellent capability of generic discriminative models (e.g. VGG19), which can guide the training process of a new generative model on multiple levels to bridge the two gaps. The high-level representations can teach the generative model to extract necessary visual information from text descriptions, which can bridge the heterogeneous gap. The mid-level and low-level representations can lead it to learn structures and details of images respectively, which relieves the homogeneous gap. Therefore, we propose Symmetrical Distillation Networks (SDN) composed of a source discriminative model as "teacher" and a target generative model as "student". The target generative model has a symmetrical structure with the source discriminative model, in order to transfer hierarchical knowledge accessibly. Moreover, we decompose the training process into two stages with different distillation paradigms for promoting the performance of the target generative model. Experiments on two widely-used datasets are conducted to verify the effectiveness of our proposed SDN.