1 code implementation • 25 Apr 2024 • Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang
The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes.
1 code implementation • 28 Feb 2024 • Xun Huang, Hai Wu, Xin Li, Xiaoliang Fan, Chenglu Wen, Cheng Wang
LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals.
1 code implementation • 27 Feb 2024 • Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, Weiming Lu
Large Language Models exhibit robust problem-solving capabilities for diverse tasks.
no code implementations • 2 Jan 2024 • Shiwen Zhao, Wei Wang, Junhui Hou, Hai Wu
This paper introduces HPC-Net, a high-precision and rapidly convergent object detection network.
no code implementations • 28 Jul 2023 • Hai Wu, Qunsong Zeng, Kaibin Huang
To overcome the bottleneck, we propose the framework of model broadcasting and assembling (MBA), which represents the first attempt on leveraging reusable knowledge, referring to shared parameters among tasks, to enable parameter broadcasting to reduce communication overhead.
1 code implementation • CVPR 2023 • Hai Wu, Chenglu Wen, Shaoshuai Shi, Xin Li, Cheng Wang
Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework.
1 code implementation • ICCV 2023 • Qiming Xia, Jinhao Deng, Chenglu Wen, Hai Wu, Shaoshuai Shi, Xin Li, Cheng Wang
Combining CoIn with an iterative training strategy, we propose a CoIn++ pipeline, which requires only 2% annotations in the KITTI dataset to achieve performance comparable to the fully supervised methods.
no code implementations • 10 Dec 2022 • Hai Wu, Ruifei He, Haoru Tan, Xiaojuan Qi, Kaibin Huang
Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width.
no code implementations • 22 Nov 2022 • Hai Wu, Chenglu Wen, Wei Li, Xin Li, Ruigang Yang, Cheng Wang
However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed.
no code implementations • 7 Oct 2022 • Kaibin Huang, Hai Wu, Zhiyan Liu, Xiaojuan Qi
We further propose a virtualized 6G network architecture customized for deploying in-situ model downloading with the key feature of a three-tier (edge, local, and central) AI library.