paper-with-me

홈 › Papers

Factor Decomposed Generative Adversarial Networks for Text-to-Image Synthesis

2023-03-24 · Jiguo Li, Xiaobin Liu, Lirong Zheng

Prior works about text-to-image synthesis typically concatenated the sentence embedding with the noise vector, while the sentence embedding and the noise vector are two different factors, which control the different aspects of the generation. Simply concatenating them will entangle the latent factors and encumber the generative model. In this paper, we attempt to decompose these two factors and propose Factor Decomposed Generative Adversarial Networks~(FDGAN). To achieve this, we firstly generate images from the noise vector and then apply the sentence embedding in the normalization layer for both generator and discriminators. We also design an additive norm layer to align and fuse the text-image features. The experimental results show that decomposing the noise and the sentence embedding can disentangle latent factors in text-to-image synthesis, and make the generative model more efficient. Compared with the baseline, FDGAN can achieve better performance, while fewer parameters are used.

📄 PDF Abstract BibTeX arXiv:2303.13821

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationSentenceSentence EmbeddingSentence-Embedding

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Style and Content Disentanglement in Generative Adversarial Networks

2018-11-14 · Hadi Kazemi, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representa…

DisentanglementGenerative Adversarial NetworkImage Generation

Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision

2019-09-19 · Yubao Liu, Kai Lin

Although many methods have been proposed to deal with nature image super-resolution (SR) and get impressive performance, the text images SR is not good due to their ignorance of document images. In this paper, we propose…

Generative Adversarial NetworkImage MattingImage Super-ResolutionSuper-Resolution

GANDA: A deep generative adversarial network predicts the spatial distribution of nanoparticles in tumor pixelly

2020-12-23 · Jiulou Zhang, Yuxia Tang, Shouju Wang

Intratumoral nanoparticles (NPs) distribution is critical for the success of nanomedicine in imaging and treatment, but computational models to describe the NPs distribution remain unavailable due to the complex tumor-na…

Generative Adversarial Networkwhole slide images

Decomposed Adversarial Learned Inference

2020-04-21 · Alexander Hanbo Li, Yaqing Wang, Changyou Chen, Jing Gao

Effective inference for a generative adversarial model remains an important and challenging problem. We propose a novel approach, Decomposed Adversarial Learned Inference (DALI), which explicitly matches prior and condit…

RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion

2022-06-28 · Dacheng Yin, Chuanxin Tang, Yanqing Liu, Xiaoqiang Wang 외

This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and …

Sentence