Zobrazeno 1 - 10
of 1 673
pro vyhledávání: '"Sui, Yi"'
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
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
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
Autor:
Enns, Benjamin1 (AUTHOR), Sui, Yi1 (AUTHOR), Guerra‐Alejos, Brenda C.1 (AUTHOR), Humphrey, Lia1 (AUTHOR), Piske, Micah1 (AUTHOR), Zang, Xiao2 (AUTHOR), Doblecki‐Lewis, Susanne3 (AUTHOR), Feaster, Daniel J.4 (AUTHOR), Frye, Victoria A.5 (AUTHOR), Geng, Elvin H.6 (AUTHOR), Liu, Albert Y.7 (AUTHOR), Marshall, Brandon D. L.8 (AUTHOR), Rhodes, Scott D.9 (AUTHOR), Sullivan, Patrick S.10 (AUTHOR), Nosyk, Bohdan1,11 (AUTHOR) bnosyk@sfu.ca
Publikováno v:
Journal of the International AIDS Society. Jul2024 Supplement 1, Vol. 27, p1-12. 12p.
Publikováno v:
IEEE Access, Vol 12, Pp 67632-67640 (2024)
The study of the influence factor of transmission line scattering and its influence law is the key to developing the transmission line passive interference suppression strategy. Therefore, the line-surface geometric model of electromagnetic scatterin
Externí odkaz:
https://doaj.org/article/0504ba6c1dce43deb740340e25253eb8
Publikováno v:
Neurology and Therapy, Vol 13, Iss 1, Pp 11-20 (2023)
Abstract Paroxysmal sympathetic hyperactivity (PSH) mainly occurs after acquired brain injury (ABI) and often presents with high fever, hypertension, tachycardia, tachypnea, sweating, and dystonia (increased muscle tone or spasticity). The pathophysi
Externí odkaz:
https://doaj.org/article/9f300c58df9647269df024fc1bafca6f
Publikováno v:
Engineering Computations, 2023, Vol. 40, Issue 6, pp. 1454-1484.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/EC-12-2021-0747