1 code implementation • 30 Nov 2022 • Siqi Fan, Fenghua Zhu, Zunlei Feng, Yisheng Lv, Mingli Song, Fei-Yue Wang
Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels.
1 code implementation • 23 Jul 2022 • Keqiang Li, Mingyang Zhao, Huaiyu Wu, Dong-Ming Yan, Zhen Shen, Fei-Yue Wang, Gang Xiong
We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds.
Ranked #3 on
Surface Normals Estimation
on PCPNet
no code implementations • 6 May 2022 • Jiaqi Gao, Jingqi Li, Hongming Shan, Yanyun Qu, James Z. Wang, Fei-Yue Wang, Junping Zhang
Crowd counting has important applications in public safety and pandemic control.
1 code implementation • 13 Jan 2022 • Jiaqi Gao, Zhizhong Huang, Yiming Lei, James Z. Wang, Fei-Yue Wang, Junping Zhang
Specifically, we propose S$^2$FPR which can extract structural information and learn partial orders of coarse-to-fine pyramid features in the latent space for better crowd counting with massive unlabeled images.
1 code implementation • CVPR 2021 • Siqi Fan, Qiulei Dong, Fenghua Zhu, Yisheng Lv, Peijun Ye, Fei-Yue Wang
For each 3D point, the local polar representation block is firstly explored to construct a spatial representation that is invariant to the z-axis rotation, then the dual-distance attentive pooling block is designed to utilize the representations of its neighbors for learning more discriminative local features according to both the geometric and feature distances among them, and finally, the global contextual feature block is designed to learn a global context for each 3D point by utilizing its spatial location and the volume ratio of the neighborhood to the global point cloud.
Ranked #1 on
Semantic Segmentation
on Toronto-3D L002
no code implementations • 15 May 2021 • Xinyu Peng, Jiawei Zhang, Fei-Yue Wang, Li Li
As a promising tool to better understand the learning dynamic of minibatch SGD, the information bottleneck (IB) theory claims that the optimization process consists of an initial fitting phase and the following compression phase.
1 code implementation • IEEE Transactions on Vehicular Technology 2021 • Siqi Fan, Fenghua Zhu, Shichao Chen, HUI ZHANG, Bin Tian, Yisheng Lv, Fei-Yue Wang
Most successful object detectors are anchor-based, which is difficult to adapt to the diversity of traffic objects.
no code implementations • 1 Jan 2021 • Xiaoshuang Li, Junchen Jin, Xiao Wang, Fei-Yue Wang
This study proposes a novel approach integrating deep Q learning from dynamic demonstrations with a behavioral cloning model (DQfDD-BC), which includes a supervised learning technique of instructing a DRL model to enhance its performance.
2 code implementations • 30 Nov 2020 • Zhenhua Shi, Dongrui Wu, Chenfeng Guo, Changming Zhao, Yuqi Cui, Fei-Yue Wang
To effectively optimize Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a mini-batch gradient descent with regularization, DropRule, and AdaBound (MBGD-RDA) algorithm was recently proposed.
no code implementations • 22 Sep 2020 • Weishan Zhang, Tao Zhou, Qinghua Lu, Xiao Wang, Chunsheng Zhu, Haoyun Sun, Zhipeng Wang, Sin Kit Lo, Fei-Yue Wang
To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections.
no code implementations • 8 Sep 2020 • Jianji Wang, Qi Liu, Shupei Zhang, Nanning Zheng, Fei-Yue Wang
By the proposed method, the computational complexity is reduced from $O(\frac{1}{6}{k^3}+mk^2+mkd)$ to $O(\frac{1}{6}{k^3}+\frac{1}{2}mk^2)$ for each candidate subset in sparse regression.
no code implementations • 7 Aug 2020 • Haiping Zhu, Hongming Shan, Yuheng Zhang, Lingfu Che, Xiaoyang Xu, Junping Zhang, Jianbo Shi, Fei-Yue Wang
We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation, which can integrate ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships.
no code implementations • 26 Jul 2020 • Teng Liu, Yang Xing, Long Chen, Dongpu Cao, Fei-Yue Wang
The objectives of the three virtual digital vehicles are interacting, guiding, simulating and improving with the real vehicles.
no code implementations • 21 Jul 2020 • Teng Liu, Xing Yang, Hong Wang, Xiaolin Tang, Long Chen, Huilong Yu, Fei-Yue Wang
The three virtual vehicles (descriptive, predictive, and prescriptive) dynamically interact with the real one in order to enhance the safety and performance of the real vehicle.
no code implementations • 25 Apr 2020 • Sicong Du, Hengkai Guo, Yao Chen, Yilun Lin, Xiangbing Meng, Linfu Wen, Fei-Yue Wang
Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems.
1 code implementation • 10 Dec 2019 • Yonglin Tian, Lichao Huang, Xuesong Li, Kunfeng Wang, Zilei Wang, Fei-Yue Wang
Varying density of point clouds increases the difficulty of 3D detection.
no code implementations • 10 Oct 2019 • Yonglin Tian, Kunfeng Wang, Yuang Wang, Yulin Tian, Zilei Wang, Fei-Yue Wang
We adopt different modalities of LiDAR data to generate richer features and present an adaptive and azimuth-aware network to aggregate local features from image, bird's eye view maps and point cloud.
no code implementations • 13 Mar 2019 • Xiuqin Shang, Dayong Shen, Fei-Yue Wang, Timo R. Nyberg
Firstly the constructive procedure creates a set of lays in sequence, and then the improving loop tries to pick each lay from the lay set and rearrange the remaining lays into a smaller lay set.
no code implementations • 12 Mar 2019 • Chao Gou, Tianyu Shen, Wenbo Zheng, Huadan Xue, Hui Yu, Qiang Ji, Zhengyu Jin, Fei-Yue Wang
Artificial imaging systems are introduced to select and prescriptively generate medical image data in a knowledge-driven way to utilize medical domain knowledge.
no code implementations • 11 Mar 2019 • Xinyu Peng, Li Li, Fei-Yue Wang
Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning.
no code implementations • 9 Mar 2019 • Jianping Cao, Senzhang Wang, Danyan Wen, Zhaohui Peng, Philip S. Yu, Fei-Yue Wang
HINT first models multi-sourced texts (e. g. news and tweets) as heterogeneous information networks by introducing the shared ``anchor texts'' to connect the comparative texts.
1 code implementation • 6 Aug 2018 • Yilun Lin, Xingyuan Dai, Li Li, Fei-Yue Wang
Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult.
no code implementations • 14 Feb 2018 • Kunfeng Wang, Chao Gou, Fei-Yue Wang
Secondly, multiple heterogeneous features (including brightness variation, chromaticity variation, and texture variation) are extracted by comparing the input frame with the background model, and a multi-source learning strategy is designed to online estimate the probability distributions for both foreground and background.
1 code implementation • 23 Dec 2017 • Wenwen Zhang, Kunfeng Wang, Hua Qu, Jihong Zhao, Fei-Yue Wang
In order to make the generic scene pedestrian detectors work well in specific scenes, the labeled data from specific scenes are needed to adapt the models to the specific scenes.
no code implementations • 22 Dec 2017 • Yonglin Tian, Xuan Li, Kunfeng Wang, Fei-Yue Wang
In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data.
no code implementations • 22 Dec 2017 • Xuan Li, Kunfeng Wang, Yonglin Tian, Lan Yan, Fei-Yue Wang
As a result, we present a viable implementation pipeline for constructing large-scale artificial scenes for traffic vision research.
no code implementations • 11 Jul 2017 • Xingyuan Dai, Rui Fu, Yilun Lin, Li Li, Fei-Yue Wang
Detrending based methods decompose original flow series into trend and residual series, in which trend describes the fixed temporal pattern in traffic flow and residual series is used for prediction.