paper-with-me

홈 › Papers

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

2023-09-07 · CVPR 2025 1 · Jiapeng Zhu, Ceyuan Yang, Kecheng Zheng, Yinghao Xu, Zifan Shi, Yujun Shen

Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution to training large-scale models with limited computational resources. Inspired by such a philosophy, we present Aurora, a GAN-based text-to-image generator that employs a collection of experts to learn feature processing, together with a sparse router to help select the most suitable expert for each feature point. To faithfully decode the sampling stochasticity and the text condition to the final synthesis, our router adaptively makes its decision by taking into account the text-integrated global latent code. At 64x64 image resolution, our model trained on LAION2B-en and COYO-700M achieves 6.2 zero-shot FID on MS COCO. We release the code and checkpoints to facilitate the community for further development.

📄 PDF Abstract BibTeX arXiv:2309.03904

Code (1)

zhujiapeng/aurora 공식 구현 pytorch

Tasks

Image GenerationMixture-of-ExpertsPhilosophyvalid

Similar Papers 제목 키워드 기반

Creative Portraiture: Exploring Creative Adversarial Networks and Conditional Creative Adversarial Networks

2024-12-10 · Sebastian Hereu, Qianfei Hu

Convolutional neural networks (CNNs) have been combined with generative adversarial networks (GANs) to create deep convolutional generative adversarial networks (DCGANs) with great success. DCGANs have been used for gene…

Hierarchical Modes Exploring in Generative Adversarial Networks

2020-03-05 · Mengxiao Hu, Jinlong Li, Maolin Hu, Tao Hu

In conditional Generative Adversarial Networks (cGANs), when two different initial noises are concatenated with the same conditional information, the distance between their outputs is relatively smaller, which makes mino…

DiversityImage GenerationText to Image GenerationText-to-Image Generation+1

Skip-Thought GAN: Generating Text through Adversarial Training using Skip-Thought Vectors

2018-10-16 · Anonymous

In the past few years, various advancements have been made in generative models owing to the formulation of Generative Adversarial Networks (GANs). GANs have been shown to perform exceedingly well on a wide variety of ta…

Image GenerationSentenceSentence EmbeddingsStyle Transfer+2

Text to Image Synthesis using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networks

2022-07-06 · Haileleol Tibebu, Aadil Malik, Varuna De Silva

Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor…

Image Generation

Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data

2021-09-29 · ICLR 2022 4 · Yaxing Wang, Joost Van de Weijer, Lu Yu, Shangling Jui

Conditional image synthesis is an integral part of many X2I translation systems, including image-to-image, text-to-image and audio-to-image translation systems. Training these large systems generally requires huge amount…

Image GenerationKnowledge DistillationSemantic SegmentationTranslation