Zobrazeno 1 - 10
of 385
pro vyhledávání: '"Li, LinYan"'
Reinforcement learning (RL) techniques have been increasingly investigated for dynamic HVAC control in buildings. However, most studies focus on exploring solutions in online or off-policy scenarios without discussing in detail the implementation fea
Externí odkaz:
http://arxiv.org/abs/2408.07986
Few-shot class-incremental learning (FSCIL) aims to build machine learning model that can continually learn new concepts from a few data samples, without forgetting knowledge of old classes. The challenges of FSCIL lies in the limited data of new cla
Externí odkaz:
http://arxiv.org/abs/2310.20268
Vehicle-to-everything (V2X) perception is an innovative technology that enhances vehicle perception accuracy, thereby elevating the security and reliability of autonomous systems. However, existing V2X perception methods focus on static scenes from m
Externí odkaz:
http://arxiv.org/abs/2310.19113
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new clas
Externí odkaz:
http://arxiv.org/abs/2303.13862
Rehearsal, retraining on a stored small data subset of old tasks, has been proven effective in solving catastrophic forgetting in continual learning. However, due to the sampled data may have a large bias towards the original dataset, retraining them
Externí odkaz:
http://arxiv.org/abs/2303.02954
Autor:
Du, Kaile, Lyu, Fan, Li, Linyan, Hu, Fuyuan, Feng, Wei, Xu, Fenglei, Xi, Xuefeng, Cheng, Hanjing
Multi-Label Continual Learning (MLCL) builds a class-incremental framework in a sequential multi-label image recognition data stream. The critical challenges of MLCL are the construction of label relationships on past-missing and future-missing parti
Externí odkaz:
http://arxiv.org/abs/2211.14763
Existing class-incremental lifelong learning studies only the data is with single-label, which limits its adaptation to multi-label data. This paper studies Lifelong Multi-Label (LML) classification, which builds an online class-incremental classifie
Externí odkaz:
http://arxiv.org/abs/2207.07840
The Lifelong Multi-Label (LML) image recognition builds an online class-incremental classifier in a sequential multi-label image recognition data stream. The key challenges of LML image recognition are the construction of label relationships on Parti
Externí odkaz:
http://arxiv.org/abs/2203.05534
Autor:
Jia, Min, Zhang, Zhe, Zhang, Li, Zhao, Liang, Lu, Xinbo, Li, Linyan, Ruan, Jianhui, Wu, Yunlong, He, Zhuoming, Liu, Mei, Jiang, Lingling, Gao, Yajing, Wu, Pengcheng, Zhu, Shuying, Niu, Muchuan, Zheng, Haitao, Cai, Bofeng, Tang, Ling, Shu, Yinbiao, Wang, Jinnan
Publikováno v:
In Applied Energy 1 November 2024 373
Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image. Offering potentials to reduce expensive manual editing, SIE has attracted much interest recently. However, existing methods can hardly produce accurate editing and e
Externí odkaz:
http://arxiv.org/abs/2110.11159