50 citations · 115 across the 6 of their papers we have counts for
9 papers · 1 filter
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
Haiyang Wang, Hao Tang, Shaoshuai Shi +4
Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems. However, current 3D perception…
CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
Haiyang Wang, Lihe Ding, Shaocong Dong +5
We present a novel two-stage fully sparse convolutional 3D object detection framework, named CAGroup3D. Our proposed method first generates some high-quality 3D proposals by levera…
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
Hanzhe Hu, Shuai Bai, Aoxue Li +2
Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annota…
Boosting Few-Shot Learning With Adaptive Margin Loss
Aoxue Li, Weiran Huang, Xu Lan +3
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. T…
Few-Shot Learning with Global Class Representations
Tiange Luo, Aoxue Li, Tao Xiang +2
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples. In ea…
Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
Zhiwu Lu, Jiechao Guan, Aoxue Li +3
Zero-shot learning (ZSL) is made possible by learning a projection function between a feature space and a semantic space (e.g.,~an attribute space). Key to ZSL is thus to learn a p…