Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Li, Daiqing"'
Autor:
Liu, Bingchen, Akhgari, Ehsan, Visheratin, Alexander, Kamko, Aleks, Xu, Linmiao, Shrirao, Shivam, Souza, Joao, Doshi, Suhail, Li, Daiqing
We introduce Playground v3 (PGv3), our latest text-to-image model that achieves state-of-the-art (SoTA) performance across multiple testing benchmarks, excels in graphic design abilities and introduces new capabilities. Unlike traditional text-to-ima
Externí odkaz:
http://arxiv.org/abs/2409.10695
In this work, we share three insights for achieving state-of-the-art aesthetic quality in text-to-image generative models. We focus on three critical aspects for model improvement: enhancing color and contrast, improving generation across multiple as
Externí odkaz:
http://arxiv.org/abs/2402.17245
Autor:
Li, Jing, Sun, Li, Wang, Yaogang, Guo, Lichuan, Li, Daiqing, Liu, Chang, Sun, Ning, Xu, Zheng, Li, Shu, Jiang, Yunwen, Wang, Yuan, Zhang, Shunming, Chen, Liming
Publikováno v:
JMIR mHealth and uHealth, Vol 8, Iss 3, p e15390 (2020)
BackgroundMobile-based interventions appear to be promising in ameliorating huge burdens experienced by patients with type 2 diabetes. However, it is unclear how effective mobile-based interventions are in glycemic management of patients with type 2
Externí odkaz:
https://doaj.org/article/1be1235726a348bfbaee7076c487ecc9
Autor:
Liu, Zelong, Zhou, Alexander, Yang, Arnold, Yilmaz, Alara, Yoo, Maxwell, Sullivan, Mikey, Zhang, Catherine, Grant, James, Li, Daiqing, Fayad, Zahi A., Huver, Sean, Deyer, Timothy, Mei, Xueyan
Deep learning in medical imaging often requires large-scale, high-quality data or initiation with suitably pre-trained weights. However, medical datasets are limited by data availability, domain-specific knowledge, and privacy concerns, and the creat
Externí odkaz:
http://arxiv.org/abs/2312.05953
Autor:
Li, Daiqing, Ling, Huan, Kar, Amlan, Acuna, David, Kim, Seung Wook, Kreis, Karsten, Torralba, Antonio, Fidler, Sanja
In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative model into st
Externí odkaz:
http://arxiv.org/abs/2307.07487
Autor:
Kim, Seung Wook, Brown, Bradley, Yin, Kangxue, Kreis, Karsten, Schwarz, Katja, Li, Daiqing, Rombach, Robin, Torralba, Antonio, Fidler, Sanja
Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3
Externí odkaz:
http://arxiv.org/abs/2304.09787
Autor:
Gao, Jun, Shen, Tianchang, Wang, Zian, Chen, Wenzheng, Yin, Kangxue, Li, Daiqing, Litany, Or, Gojcic, Zan, Fidler, Sanja
As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train performan
Externí odkaz:
http://arxiv.org/abs/2209.11163
Autor:
Mahmood, Rafid, Lucas, James, Acuna, David, Li, Daiqing, Philion, Jonah, Alvarez, Jose M., Yu, Zhiding, Fidler, Sanja, Law, Marc T.
Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance? This question is of critical importance in applications such as autonomous driving or medical imaging where co
Externí odkaz:
http://arxiv.org/abs/2207.01725
Modern image generative models show remarkable sample quality when trained on a single domain or class of objects. In this work, we introduce a generative adversarial network that can simultaneously generate aligned image samples from multiple relate
Externí odkaz:
http://arxiv.org/abs/2206.02903
Autor:
Li, Daiqing, Ling, Huan, Kim, Seung Wook, Kreis, Karsten, Barriuso, Adela, Fidler, Sanja, Torralba, Antonio
Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small set of ma
Externí odkaz:
http://arxiv.org/abs/2201.04684