480 citations · 721 across the 18 of their papers we have counts for
7 papers · 2 filters
DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention
Zhipeng Luo, Changqing Zhou, Gongjie Zhang +1
3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse atten…
Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer
Zhipeng Luo, Changqing Zhou, Liang Pan +6
With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the…
TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection
Zhipeng Luo, Gongjie Zhang, Changqing Zhou +3
3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics. However, most existing studies focus on s…
Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Gongjie Zhang, Zhipeng Luo, Zichen Tian +3
Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transfo…
Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation
Gongjie Zhang, Zhipeng Luo, Kaiwen Cui +2
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still c…
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
Gongjie Zhang, Zhipeng Luo, Jiaxing Huang +2
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hin…
Accelerating DETR Convergence via Semantic-Aligned Matching
Gongjie Zhang, Zhipeng Luo, Yingchen Yu +2
The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extre…