Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Lv, Jinhu"'
In this paper, we consider the distributed filtering problem over sensor networks such that all sensors cooperatively track unknown time-varying parameters by using local information. A distributed forgetting factor least squares (FFLS) algorithm is
Externí odkaz:
http://arxiv.org/abs/2310.06287
Autor:
Wang, Runqi, Duan, Xiaoyue, Kang, Guoliang, Liu, Jianzhuang, Lin, Shaohui, Xu, Songcen, Lv, Jinhu, Zhang, Baochang
Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which consists of a feature extractor and a classifier. The feature extracto
Externí odkaz:
http://arxiv.org/abs/2305.11488
Autor:
Xu, Sheng, Li, Yanjing, Ma, Teli, Lin, Mingbao, Dong, Hao, Zhang, Baochang, Gao, Peng, Lv, Jinhu
Binary neural networks (BNNs) have received ever-increasing popularity for their great capability of reducing storage burden as well as quickening inference time. However, there is a severe performance drop compared with real-valued networks, due to
Externí odkaz:
http://arxiv.org/abs/2302.00956
Autor:
Xu, Sheng, Li, Yanjing, Zeng, Bohan, ma, Teli, Zhang, Baochang, Cao, Xianbin, Gao, Peng, Lv, Jinhu
Knowledge distillation (KD) has been proven to be useful for training compact object detection models. However, we observe that KD is often effective when the teacher model and student counterpart share similar proposal information. This explains why
Externí odkaz:
http://arxiv.org/abs/2210.03477
Autor:
Xu, Sheng, Li, Yanjing, Wang, Tiancheng, Ma, Teli, Zhang, Baochang, Gao, Peng, Qiao, Yu, Lv, Jinhu, Guo, Guodong
Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an essential role in reducing the performance gap to their real-valued counte
Externí odkaz:
http://arxiv.org/abs/2209.01542
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary vision transfo
Externí odkaz:
http://arxiv.org/abs/2201.08050
Autor:
Qu, Qingyu, Li, Xijun, Zhou, Yunfan, Zeng, Jia, Yuan, Mingxuan, Wang, Jie, Lv, Jinhu, Liu, Kexin, Mao, Kun
Most combinatorial optimization problems can be formulated as mixed integer linear programming (MILP), in which branch-and-bound (B\&B) is a general and widely used method. Recently, learning to branch has become a hot research topic in the intersect
Externí odkaz:
http://arxiv.org/abs/2201.06213
Distributed Nash equilibrium (NE) seeking problem for multi-coalition games has attracted increasing attention in recent years, but the research mainly focuses on the case without agreement demand within coalitions. This paper considers a class of ne
Externí odkaz:
http://arxiv.org/abs/2106.10513
This paper mainly discusses the diffusion on complex networks with time-varying couplings. We propose a model to describe the adaptive diffusion process of local topological and dynamical information, and find that the Barabasi-Albert scale-free netw
Externí odkaz:
http://arxiv.org/abs/1812.03814
Publikováno v:
In Aerospace Science and Technology October 2021 117
