41 citations · 42 across the 4 of their papers we have counts for
5 papers
H2-Mapping: Real-time Dense Mapping Using Hierarchical Hybrid Representation
Chenxing Jiang, Hanwen Zhang, Peize Liu +4
Constructing a high-quality dense map in real-time is essential for robotics, AR/VR, and digital twins applications. As Neural Radiance Field (NeRF) greatly improves the mapping pe…
Improving Knowledge Distillation via Transferring Learning Ability
Long Liu, Tong Li, Hui Cheng
Existing knowledge distillation methods generally use a teacher-student approach, where the student network solely learns from a well-trained teacher. However, this approach overlo…
PCB-RandNet: Rethinking Random Sampling for LIDAR Semantic Segmentation in Autonomous Driving Scene
XianFeng Han, Huixian Cheng, Hang Jiang +2
Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods ma…
Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis
Haifan Gong, Hui Cheng, Yifan Xie +4
Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image. However, the label obtained by the cytological biopsy…
Dual Transformer for Point Cloud Analysis
Xian-Feng Han, Yi-Fei Jin, Hui-Xian Cheng +1
Following the tremendous success of transformer in natural language processing and image understanding tasks, in this paper, we present a novel point cloud representation learning…