Zobrazeno 1 - 10
of 1 838
pro vyhledávání: '"SUI, Yi"'
Although conformal prediction is a promising method for quantifying the uncertainty of machine learning models, the prediction sets it outputs are not inherently actionable. Many applications require a single output to act on, not several. To overcom
Externí odkaz:
http://arxiv.org/abs/2410.01888
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
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
Autor:
LIU Wenli (刘文丽), GUO Haijiao (果海姣), SONG Ying (宋颖), SUI Yi (孙祎), GAO Jiajia (高佳佳), MA Xiaoxu (马晓旭), CHEN Cheng (陈程)
Publikováno v:
中西医结合护理, Vol 10, Iss 7, Pp 37-40 (2024)
Objective To investigate the effect of Tuina combined with auricular acupoint pressing therapy in the treatment of post-stroke constipation. Methods Totally 100 bedridden patients with post-stroke constipation were randomly divided in the observation
Externí odkaz:
https://doaj.org/article/06cdc69b26164d2dba99421b8eaf73cc
Publikováno v:
ILR Review; Oct2024, Vol. 77 Issue 5, p813-824, 12p
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