no code implementations • 28 Feb 2024 • Mingxin Li, Richong Zhang, Zhijie Nie
To address these questions, we start from the perspective of gradients and discover that four effective contrastive losses can be integrated into a unified paradigm, which depends on three components: the Gradient Dissipation, the Weight, and the Ratio.
1 code implementation • 12 Sep 2023 • Mingxin Li, Richong Zhang, Zhijie Nie, Yongyi Mao
An intriguing phenomenon in CSE is the significant performance gap between supervised and unsupervised methods, with their only difference lying in the training data.
no code implementations • 23 Jun 2022 • Xia Hua, Mingxin Li, Junxiong Fei, Yu Shi, Jianguo Liu, Hanyu Hong
In most of these networks, only the features refined by the attention maps can be passed to the next layer and the attention maps of different layers are separated from each other, which does not make full use of the attention information from different layers in the CNN.
no code implementations • 19 Mar 2022 • Yibo Guo, Lishuo Hou, Mingxin Li, Yue Yuan, Shun Liu, Jingyi Xue, Yafang Han, Mingliang Xu
In this paper, we propose a P-MADDPG algorithm to solve the emergency decision-making problem of emergent incidents, which predicts the nodes where an incident may occur in the next time by GRU model and makes decisions before the incident occurs, thus solving the problem that the decision speed cannot keep up with the spreading speed.
no code implementations • 6 Jan 2021 • Jixing Zhang, Heng Yuan, Tianzheng Liu, Lixia Xu, Guodong Bian, Pengcheng Fan, Mingxin Li
This article proposes a scheme for nitrogen-vacancy (NV) center magnetometry that combines the advantages of lock-in detection and pulse-type scheme.
Applied Physics Quantum Physics