Zobrazeno 1 - 10
of 85
pro vyhledávání: '"Gao, Dashan"'
Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While existing CL methods accomplish this to some extent, they are still prone to
Externí odkaz:
http://arxiv.org/abs/2306.08200
Cross-platform recommendation aims to improve recommendation accuracy by gathering heterogeneous features from different platforms. However, such cross-silo collaborations between platforms are restricted by increasingly stringent privacy protection
Externí odkaz:
http://arxiv.org/abs/2305.06272
Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the robustness a
Externí odkaz:
http://arxiv.org/abs/2304.03955
Autor:
Zhang, Renhong, Cheng, Tianheng, Yang, Shusheng, Jiang, Haoyi, Zhang, Shuai, Lyu, Jiancheng, Li, Xin, Ying, Xiaowen, Gao, Dashan, Liu, Wenyu, Wang, Xinggang
Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tr
Externí odkaz:
http://arxiv.org/abs/2303.17594
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is added per task. While effective from a computational standpoint, these me
Externí odkaz:
http://arxiv.org/abs/2303.12696
Federated learning (FL) has been proposed to protect data privacy and virtually assemble the isolated data silos by cooperatively training models among organizations without breaching privacy and security. However, FL faces heterogeneity from various
Externí odkaz:
http://arxiv.org/abs/2210.04505
Autor:
Gao, Dashan.
Publikováno v:
Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses
Thesis (Ph. D.)--University of California, San Diego, 2008.
Title from first page of PDF file (viewed September 22, 2008). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 145-162).
Title from first page of PDF file (viewed September 22, 2008). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 145-162).
Externí odkaz:
http://wwwlib.umi.com/cr/ucsd/fullcit?p3320150
Matrix Factorization has been very successful in practical recommendation applications and e-commerce. Due to data shortage and stringent regulations, it can be hard to collect sufficient data to build performant recommender systems for a single comp
Externí odkaz:
http://arxiv.org/abs/2007.01587
Autor:
Ju, Ce, Zhao, Ruihui, Sun, Jichao, Wei, Xiguang, Zhao, Bo, Liu, Yang, Li, Hongshan, Chen, Tianjian, Zhang, Xinwei, Gao, Dashan, Tan, Ben, Yu, Han, He, Chuning, Jin, Yuan
Prevention of stroke with its associated risk factors has been one of the public health priorities worldwide. Emerging artificial intelligence technology is being increasingly adopted to predict stroke. Because of privacy concerns, patient data are s
Externí odkaz:
http://arxiv.org/abs/2006.10517
Publikováno v:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020, pp. 3040-3045
The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets. Privacy concerns associated with EEG signals limi
Externí odkaz:
http://arxiv.org/abs/2004.12321