no code implementations • 5 Mar 2024 • Jiawei Hou, Xiaoyan Li, Wenhao Guan, Gang Zhang, Di Feng, Yuheng Du, xiangyang xue, Jian Pu
In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view (BEV) semantic segmentation.
no code implementations • 13 Oct 2023 • Feng Jiang, Chaoping Tu, Gang Zhang, Jun Li, Hanqing Huang, Junyu Lin, Di Feng, Jian Pu
LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios.
no code implementations • 26 Sep 2023 • Zizhang Wu, Zhuozheng Li, Zhi-Gang Fan, Yunzhe Wu, Xiaoquan Wang, Rui Tang, Jian Pu
Monocular depth estimation is challenging due to its inherent ambiguity and ill-posed nature, yet it is quite important to many applications.
1 code implementation • 22 Sep 2023 • Yuxiang Yan, Boda Liu, Jianfei Ai, Qinbu Li, Ru Wan, Jian Pu
To address this, we introduce PointSSC, the first cooperative vehicle-infrastructure point cloud benchmark for semantic scene completion.
no code implementations • 20 Sep 2023 • Zizhang Wu, Xinyuan Chen, Fan Song, Yuanzhu Gan, Tianhao Xu, Jian Pu, Rui Tang
In this paper, wepresent the Parking Pedestrian Dataset (PPD), a large-scale fisheye dataset to support research dealing with real-world pedestrians, especially with occlusions and diverse postures.
no code implementations • 19 Sep 2023 • Zizhang Wu, Yuanzhu Gan, Tianhao Xu, Rui Tang, Jian Pu
We aim for accurate and efficient line landmark detection for valet parking, which is a long-standing yet unsolved problem in autonomous driving.
no code implementations • 19 Jun 2023 • Xianhui Cheng, Shoumeng Qiu, Zhikang Zou, Jian Pu, xiangyang xue
In this paper, we propose a framework named the Adaptive Distance Interval Separation Network (ADISN) that adopts a novel perspective on understanding depth maps, as a form that lies between LiDAR and images.
no code implementations • 12 May 2023 • Zizhang Wu, Zhuozheng Li, Zhi-Gang Fan, Yunzhe Wu, Yuanzhu Gan, Jian Pu, Xianzhi Li
During the refinement process, context-aware temporal attention (CTA) is developed to capture the global temporal-context correlations to maintain the feature consistency and estimation integrity of moving objects.
1 code implementation • 28 Apr 2023 • Shoumeng Qiu, Feng Jiang, Haiqiang Zhang, xiangyang xue, Jian Pu
In this paper, we propose a novel multi-to-single knowledge distillation framework for the 3D point cloud semantic segmentation task to boost the performance of those hard classes.
1 code implementation • 22 Apr 2023 • Feng Jiang, Heng Gao, Shoumeng Qiu, Haiqiang Zhang, Ru Wan, Jian Pu
However, it is difficult for existing models to achieve both high inference speed and accuracy simultaneously.
1 code implementation • 25 Feb 2023 • Jiawei Hou, Qi Chen, Yurong Cheng, Guang Chen, xiangyang xue, Taiping Zeng, Jian Pu
However, there is a lack of underground parking scenario datasets with multiple sensors and well-labeled images that support both SLAM tasks and perception tasks, such as semantic segmentation and parking slot detection.
no code implementations • 21 Feb 2023 • Zizhang Wu, Guilian Chen, Yuanzhu Gan, Lei Wang, Jian Pu
To achieve so, we inject the semantic alignment into the radar features via the semantic-aligned radar encoder (SARE) to produce image-guided radar features.
Ranked #7 on 3D Object Detection on nuscenes Camera-Radar
no code implementations • 21 Feb 2023 • Zizhang Wu, Yuanzhu Gan, Lei Wang, Guilian Chen, Jian Pu
Monocular 3D object detection reveals an economical but challenging task in autonomous driving.
no code implementations • 30 Nov 2022 • Zizhang Wu, Yunzhe Wu, Jian Pu, Xianzhi Li, Xiaoquan Wang
Specifically, we leverage intermediate features and responses for knowledge distillation.
1 code implementation • CVPR 2023 • Jie Chen, Zilong Li, Yin Zhu, Junping Zhang, Jian Pu
We design a simple yet effective HopGNN framework that can easily utilize existing GNNs to achieve hop interaction.
1 code implementation • 18 Oct 2022 • Jie Chen, Shouzhen Chen, Mingyuan Bai, Junbin Gao, Junping Zhang, Jian Pu
Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information.
no code implementations • 30 May 2022 • Jie Chen, Weiqi Liu, Zhizhong Huang, Junbin Gao, Junping Zhang, Jian Pu
The performance of GNNs degrades as they become deeper due to the over-smoothing.
Ranked #8 on Node Classification on Squirrel
1 code implementation • 19 Mar 2022 • Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang, Junping Zhang, Jian Pu
Moreover, we propose a simple yet effective Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets by learning the neighbor effect for each node.
1 code implementation • 1 Feb 2022 • Jie Chen, Weiqi Liu, Jian Pu
Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process.
no code implementations • 28 Apr 2021 • Jie Chen, Shouzhen Chen, Mingyuan Bai, Jian Pu, Junping Zhang, Junbin Gao
In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.
1 code implementation • 27 Mar 2021 • Yiqun Liu, Yi Zeng, Jian Pu, Hongming Shan, Peiyang He, Junping Zhang
In this work, we propose a self-supervised gait recognition method, termed SelfGait, which takes advantage of the massive, diverse, unlabeled gait data as a pre-training process to improve the representation abilities of spatiotemporal backbones.
no code implementations • 26 Jun 2018 • Li Wang, Weiyuan Shao, Yao Lu, Hao Ye, Jian Pu, Yingbin Zheng
Crowd counting is one of the core tasks in various surveillance applications.
no code implementations • 15 Jan 2018 • Ao Zhang, Nan Li, Jian Pu, Jun Wang, Junchi Yan, Hongyuan Zha
Learning a classifier with control on the false-positive rate plays a critical role in many machine learning applications.