794 citations · 4.4k across the 64 of their papers we have counts for
64 papers
Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling
Yan Xu, Junyi Lin, Jianping Shi +3
The correct ego-motion estimation basically relies on the understanding of correspondences between adjacent LiDAR scans. However, given the complex scenarios and the low-resolution…
Towards Balanced Learning for Instance Recognition
Jiangmiao Pang, Kai Chen, Qi Li +5
Instance recognition is rapidly advanced along with the developments of various deep convolutional neural networks. Compared to the architectures of networks, the training process,…
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
Qiqi Gu, Qianyu Zhou, Minghao Xu +5
Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external en…
Context-Aware Mixup for Domain Adaptive Semantic Segmentation
Qianyu Zhou, Zhengyang Feng, Qiqi Gu +5
Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always re…
Self-Adversarial Disentangling for Specific Domain Adaptation
Qianyu Zhou, Qiqi Gu, Jiangmiao Pang +2
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent…
BoundarySqueeze: Image Segmentation as Boundary Squeezing
Hao He, Xiangtai Li, Yibo Yang +5
This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing…
PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
Xiangtai Li, Hao He, Xia Li +6
Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two…
Enhanced Boundary Learning for Glass-like Object Segmentation
Hao He, Xiangtai Li, Guangliang Cheng +5
Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. Howev…
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
Shaoshuai Shi, Li Jiang, Jiajun Deng +5
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Regio…
FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds
Tai Wang, Conghui He, Zhe Wang +2
Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems. These LiDAR-based solutions are typ…
SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
Yan Xu, Zhaoyang Huang, Kwan-Yee Lin +5
Recent learning-based LiDAR odometry methods have demonstrated their competitiveness. However, most methods still face two substantial challenges: 1) the 2D projection representati…
Channel-wise Alignment for Adaptive Object Detection
Hang Yang, Shan Jiang, Xinge Zhu +4
Generic object detection has been immensely promoted by the development of deep convolutional neural networks in the past decade. However, in the domain shift circumstance, the cha…
Understanding the wiring evolution in differentiable neural architecture search
Sirui Xie, Shoukang Hu, Xinjiang Wang +4
Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underl…
Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Xiangtai Li, Xia Li, Li Zhang +5
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by mu…
TSIT: A Simple and Versatile Framework for Image-to-Image Translation
Liming Jiang, Changxu Zhang, Mingyang Huang +3
We introduce a simple and versatile framework for image-to-image translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generat…
Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization
Haibao Yu, Qi Han, Jianbo Li +3
Emergent hardwares can support mixed precision CNN models inference that assign different bitwidths for different layers. Learning to find an optimal mixed precision model that can…
SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Xinge Zhu, Yuexin Ma, Tai Wang +3
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds. Due to the nature of point clouds, i.e. unstructured, sparse and noi…
TPNet: Trajectory Proposal Network for Motion Prediction
Liangji Fang, Qinhong Jiang, Jianping Shi +1
Making accurate motion prediction of the surrounding traffic agents such as pedestrians, vehicles, and cyclists is crucial for autonomous driving. Recent data-driven motion predict…
Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
Qianyu Zhou, Zhengyang Feng, Qiqi Gu +4
Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeabl…
DMT: Dynamic Mutual Training for Semi-Supervised Learning
Zhengyang Feng, Qianyu Zhou, Qiqi Gu +5
Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Se…
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Xiao Song, Guorun Yang, Xinge Zhu +3
Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite poor. A…
Temporal Pyramid Network for Action Recognition
Ceyuan Yang, Yinghao Xu, Jianping Shi +2
Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often ca…
DSNAS: Direct Neural Architecture Search without Parameter Retraining
Shoukang Hu, Sirui Xie, Hehui Zheng +4
If NAS methods are solutions, what is the problem? Most existing NAS methods require two-stage parameter optimization. However, performance of the same architecture in the two stag…
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Mingyu Ding, Yuqi Huo, Hongwei Yi +4
3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task…