Zobrazeno 1 - 10
of 443
pro vyhledávání: '"You, Jane"'
Autor:
Huang, Yongsong, Xie, Wanqing, Li, Mingzhen, Cheng, Mingmei, Wu, Jinzhou, Wang, Weixiao, You, Jane, Liu, Xiaofeng
Publikováno v:
In: Frangi, A., de Bruijne, M., Wassermann, D., Navab, N. (eds) Information Processing in Medical Imaging. IPMI 2023. Lecture Notes in Computer Science, vol 13939. Springer, Cham
Federated learning (FL) enables multiple client medical institutes collaboratively train a deep learning (DL) model with privacy protection. However, the performance of FL can be constrained by the limited availability of labeled data in small instit
Externí odkaz:
http://arxiv.org/abs/2310.15371
Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, i
Externí odkaz:
http://arxiv.org/abs/2208.12885
Autor:
Liu, Xiaofeng, Guo, Zhenhua, Li, Site, Xing, Fangxu, You, Jane, Kuo, C. -C. Jay, Fakhri, Georges El, Woo, Jonghye
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both $p(x|y)$ and $p(y)$. Since the label is inaccessible in the t
Externí odkaz:
http://arxiv.org/abs/2107.13469
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discrete labels. However, in many tasks (e.g., medical diagnosis), the label
Externí odkaz:
http://arxiv.org/abs/2107.13467
The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk of misclassification which is usually measured by the distance between
Externí odkaz:
http://arxiv.org/abs/2105.00101
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the target doma
Externí odkaz:
http://arxiv.org/abs/2101.00316
Autor:
Liu, Xiaofeng, Liu, Xiongchang, Hu, Bo, Ji, Wenxuan, Xing, Fangxu, Lu, Jun, You, Jane, Kuo, C. -C. Jay, Fakhri, Georges El, Woo, Jonghye
Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain
Externí odkaz:
http://arxiv.org/abs/2101.00318
This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB images of a sequence, while the off-the-shelf and valuable expression-
Externí odkaz:
http://arxiv.org/abs/2101.00317
Autor:
Liu, Xiaofeng, Han, Yuzhuo, Bai, Song, Ge, Yi, Wang, Tianxing, Han, Xu, Li, Site, You, Jane, Lu, Ju
Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved significant progress w.
Externí odkaz:
http://arxiv.org/abs/2010.12440
How to extract effective expression representations that invariant to the identity-specific attributes is a long-lasting problem for facial expression recognition (FER). Most of the previous methods process the RGB images of a sequence, while we argu
Externí odkaz:
http://arxiv.org/abs/2010.10637