Zobrazeno 1 - 10
of 1 714
pro vyhledávání: '"Sui Yi"'
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-20 (2023)
Abstract This research delineates the energy dissipation characteristics in coal crushing under impact loads, leveraging the capabilities of Separated Hopkinson Pressure Bar experimental system. A meticulous examination of both burst-prone and non-bu
Externí odkaz:
https://doaj.org/article/4509a1aaf23a4949b45cd47ebce5f8ac
Autor:
Kowalczuk, Antoni, Dubiński, Jan, Ghomi, Atiyeh Ashari, Sui, Yi, Stein, George, Wu, Jiapeng, Cresswell, Jesse C., Boenisch, Franziska, Dziedzic, Adam
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single task, name
Externí odkaz:
http://arxiv.org/abs/2407.12588
Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed success in i
Externí odkaz:
http://arxiv.org/abs/2404.17489
Autor:
Xuting Zhang, Wansi Zhong, Xiaodong Ma, Xiaoling Zhang, Hongfang Chen, Zhimin Wang, Min Lou, GIANT Investigators, Yong Bi, Xueli Cai, Chaochan Cheng, Qun Gu, Shuangxing Hou, Haifang Hu, Huadong Huang, Likang Lan, Yaxian Wang, Dongjuan Xu, Sui Yi, Dechou Zhang, Ningyuan Zhang, Jianbin Zhong, Lianjiang Zhong
Publikováno v:
Frontiers in Pharmacology, Vol 12 (2021)
Background and Purpose: We aimed to investigate the effect of Ginkgolide® treatment on neurological function in patients receiving intravenous (IV) recombinant tissue plasminogen activator (rt-PA).Methods: This cluster randomized controlled trial in
Externí odkaz:
https://doaj.org/article/c9c35434375f441f98fa3223e6823cff
In response to everyday queries, humans explicitly signal uncertainty and offer alternative answers when they are unsure. Machine learning models that output calibrated prediction sets through conformal prediction mimic this human behaviour; larger s
Externí odkaz:
http://arxiv.org/abs/2401.13744
360{\deg} spherical images have advantages of wide view field, and are typically projected on a planar plane for processing, which is known as equirectangular image. The object shape in equirectangular images can be distorted and lack translation inv
Externí odkaz:
http://arxiv.org/abs/2310.09122
Autor:
Sui, Yi, Wu, Tongzi, Cresswell, Jesse C., Wu, Ga, Stein, George, Huang, Xiao Shi, Zhang, Xiaochen, Volkovs, Maksims
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms push the boundaries of performanc
Externí odkaz:
http://arxiv.org/abs/2310.07756
Autor:
Sui Yi, Zhang Honghai
Publikováno v:
E3S Web of Conferences, Vol 236, p 05078 (2021)
In the context of the era of intelligence, the capacity and function of data is expanding, and is playing an irreplaceable role in the field of sports news. This paper studies the data expression mode of sports news. From the point of user needs and
Externí odkaz:
https://doaj.org/article/73af41f52e2a422ebf3d991abca4f931
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
Autor:
Stein, George, Cresswell, Jesse C., Hosseinzadeh, Rasa, Sui, Yi, Ross, Brendan Leigh, Villecroze, Valentin, Liu, Zhaoyan, Caterini, Anthony L., Taylor, J. Eric T., Loaiza-Ganem, Gabriel
Publikováno v:
Thirty-seventh Conference on Neural Information Processing Systems (2023)
We systematically study a wide variety of generative models spanning semantically-diverse image datasets to understand and improve the feature extractors and metrics used to evaluate them. Using best practices in psychophysics, we measure human perce
Externí odkaz:
http://arxiv.org/abs/2306.04675
In the traditional federated learning setting, a central server coordinates a network of clients to train one global model. However, the global model may serve many clients poorly due to data heterogeneity. Moreover, there may not exist a trusted cen
Externí odkaz:
http://arxiv.org/abs/2210.06597