ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts-Reference-Cited by-同舟云学术

ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Feng Zhida¹,Zhang Zhenyu¹,Yu Xintong¹,Fang Yewei¹,Li Lanxin¹,Chen Xuyi¹,Lu Yuxiang¹,Liu Jiaxiang¹,Yin Weichong¹,Feng Shikun¹,Sun Yu¹,Chen Li²,Tian Hao¹,Wu Hua¹,Wang Haifeng¹

Affiliation:

1. Baidu Inc.

2. School of Computer Science and Technology, Wuhan University of Science and Technology

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10203671.pdf?arnumber=10203671

Reference47 articles.

1. Branch-train-merge: Embarrassingly parallel training of expert language models;li;CoRR,2022

2. ERNIE 2.0: A continual pre-training framework for language understanding;sun;The Thirty-Fourth AAAI Conference on Artificial Intelligence AAAI 2020 The Thirty-Second Innovative Applications of Artificial Intelligence Conference IAAI 2020 The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence EAAI 2020 New York NY USA February 7-12 2020,2020

3. Gshard: Scaling giant models with conditional computation and automatic sharding;lepikhin;9th International Conference on Learning Representations ICLR 2021 Virtual Event Austria May 3-7 2021,2021

4. ERNIE: enhanced representation through knowledge integration;sun;CoRR,2019

5. Decoupled weight decay regularization;loshchilov;7th International Conference on Learning Representations ICLR 2019 New Orleans LA USA May 6-9 2019,2019

Cited by 21 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. From text to mask: Localizing entities using the attention of text-to-image diffusion models;Neurocomputing;2024-12

2. TDG-Diff: Advancing customized text-to-image synthesis with two-stage diffusion guidance;Computers & Graphics;2024-08

3. DisenDreamer: Subject-Driven Text-to-Image Generation With Sample-Aware Disentangled Tuning;IEEE Transactions on Circuits and Systems for Video Technology;2024-08

4. Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13

5. Generative AI Beyond LLMs: System Implications of Multi-Modal Generation;2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS);2024-05-05