no code implementations • 7 May 2021 • Shaokui Jiang, Baile Xu, Jian Zhao, Furao Shen
With the development of the deep network and the release for a series of large scale datasets for single object tracking, siamese networks have been proposed and perform better than most of the traditional methods.
1 code implementation • 29 May 2019 • Yang Yao, Xu Zhang, Baile Xu, Furao Shen, Jian Zhao
Recent studies have demonstrated that the convolutional networks heavily rely on the quality and quantity of generated features.
no code implementations • 20 May 2019 • Xu Zhang, Yang Yao, Baile Xu, Lekun Mao, Furao Shen, Jian Zhao, QIngwei Lin
In this paper, it is the first time to discuss the difficulty without support of old classes in class incremental learning, which is called as softmax suppression problem.
4 code implementations • 2 Apr 2019 • Yi Yang, Baile Xu, Furao Shen, Jian Zhao
Many deep models are proposed to automatically learn high-order feature interactions.