# CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis

arXiv: https://arxiv.org/abs/1912.08562 · HTML: https://mlsanity.com/paper/1912.08562/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 9 of 9)

- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP](https://mlsanity.com/paper/2203.00386/) (2022)
- [Towards Open-World Text-Guided Face Image Generation and Manipulation](https://mlsanity.com/paper/2104.08910/) (2021)
- [TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2112.01398/) (2021)
- [CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation](https://mlsanity.com/paper/2107.13516/) (2021)
- [DR-GAN: Distribution Regularization for Text-to-Image Generation](https://mlsanity.com/paper/2204.07945/) (2022)
- [CAGAN: Text-To-Image Generation with Combined Attention GANs](https://mlsanity.com/paper/2104.12663/) (2021)
- [The Right Losses for the Right Gains: Improving the Semantic Consistency of Deep Text-to-Image Generation with Distribution-Sensitive Losses](https://mlsanity.com/paper/2312.10854/) (2023)

## Abstract (arXiv)

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly. It is fairly arduous due to the cross-modality translation. In this paper we circumvent this problem by focusing on parsing the content of both the input text and the synthesized image thoroughly to model the text-to-image consistency in the semantic level. Particularly, we design a memory structure to parse the textual content by exploring semantic correspondence between each word in the vocabulary to its various visual contexts across relevant images during text encoding. Meanwhile, the synthesized image is parsed to learn its semantics in an object-aware manner. Moreover, we customize a conditional discriminator to model the fine-grained correlations between words and image sub-regions to push for the text-image semantic alignment. Extensive experiments on COCO dataset manifest that our model advances the state-of-the-art performance significantly (from 35.69 to 52.73 in Inception Score).