3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration

no code implementations • 12 Nov 2024 • Liyuan Zhang, Le Hui, Qi Liu, Bo Li, Yuchao Dai

Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene.

Object Point Cloud Registration

Learning with Dynamics: Autonomous Regulation of UAV Based Communication Networks with Dynamic UAV Crew

no code implementations • 25 Sep 2024 • Ran Zhang, Bowei Li, Liyuan Zhang, Jiang, Xie, Miao Wang

To handle the dynamic environments in UCNs, reinforcement learning (RL) has been a promising solution attributed to its strong capability of adaptive decision-making free of the environment models.

Decision Making Reinforcement Learning (RL)

On the Robustness of Domain Adaption to Adversarial Attacks

no code implementations • 4 Aug 2021 • Liyuan Zhang, YuHang Zhou, Lei Zhang

State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA).

Adversarial Attack Pseudo Label +1

Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN

no code implementations • journal 2018 • Liyuan Zhang, Huamin Yang, Zhengang Jiang

Results To evaluate the classification performance of the proposed method, numerical experiments are conducted on four real-world biomedical datasets.

Classification Computational Efficiency +1