Zobrazeno 1 - 10
of 150
pro vyhledávání: '"Pan, Siyuan"'
The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these approaches typica
Externí odkaz:
http://arxiv.org/abs/2406.00210
The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model. Although there have been some attempts to reduce sampling steps, model distillation, and network quantization, these
Externí odkaz:
http://arxiv.org/abs/2312.15516
Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative loss func
Externí odkaz:
http://arxiv.org/abs/2305.14403
Autor:
Hou, Liang, Cao, Qi, Yuan, Yige, Zhao, Songtao, Ma, Chongyang, Pan, Siyuan, Wan, Pengfei, Wang, Zhongyuan, Shen, Huawei, Cheng, Xueqi
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the a
Externí odkaz:
http://arxiv.org/abs/2205.15677
Publikováno v:
In Separation and Purification Technology 15 July 2024 340
Publikováno v:
In Precision Engineering June 2024 88:1028-1039
Conditional generative models aim to learn the underlying joint distribution of data and labels to achieve conditional data generation. Among them, the auxiliary classifier generative adversarial network (AC-GAN) has been widely used, but suffers fro
Externí odkaz:
http://arxiv.org/abs/2107.10060
Publikováno v:
In Chemosphere February 2024 349
Autor:
Liang, Ziteng, Xiao, Yao, Wang, Kangjun, Jin, Yanting, Pan, Siyuan, Zhang, Jiangwei, Wu, Yuqi, Su, Yu, Zhong, Haoyue, Yang, Yong
Publikováno v:
In Energy Storage Materials November 2023 63
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.