A structure-aware framework of unsupervised cross-modality domain adaptation via frequency and spatial knowledge distillation

S Liu, S Yin, L Qu, M Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) aims to train a model on a labeled source domain
and adapt it to an unlabeled target domain. In medical image segmentation field, most …

Self-supervised boundary point prediction task for point cloud domain adaptation

J Chen, Y Zhang, K Huang, F Ma… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) could significantly improve the cross-domain
performance of current supervised 3D deep learning methods and have a widespread …

3DFFL: privacy-preserving Federated Few-Shot Learning for 3D point clouds in autonomous vehicles

AA Khan, KM Ahmad, S Shafiq, W Amin, R Kumar - Scientific Reports, 2024 - nature.com
This paper presents a comprehensive study of 3D point cloud Federated Few-Shot Learning
(3DFFL), focusing on addressing challenges such as limited data availability and privacy …

Sim-to-real grasp detection with global-to-local rgb-d adaptation

H Ma, R Qin, M Shi, B Gao… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
This paper focuses on the sim-to-real issue of RGB-D grasp detection and formulates it as a
domain adaptation problem. In this case, we present a global-to-local method to address …

GPDAN: Grasp pose domain adaptation network for sim-to-real 6-DoF object grasping

L Zheng, W Ma, Y Cai, T Lu… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
In this letter, we propose a novel Grasp Pose Domain Adaptation Network (GPDAN) to
achieve sim-to-real domain adaptation for 6-DoF grasp pose detection. The main task of …

Generalizable Face Landmarking Guided by Conditional Face Warping

J Liang, H Liu, H Xu, D Luo - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
As a significant step for human face modeling editing and generation face landmarking aims
at extracting facial keypoints from images. A generalizable face landmarker is required in …

Evolutionary multitasking with two-level knowledge transfer for multi-view point cloud registration

H Ding, H Xu, Y Wu, H Li, M Gong, W Ma… - Proceedings of the …, 2024 - dl.acm.org
Point cloud registration is a hot research topic in the field of computer vision. In recent years,
the registration method based on evolutionary computation has attracted more and more …

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification

K Fu, X Luo, L Qu, S Wang, Y Xiong… - arXiv preprint arXiv …, 2024 - arxiv.org
The expensive fine-grained annotation and data scarcity have become the primary
obstacles for the widespread adoption of deep learning-based Whole Slide Images (WSI) …

Land Cover Classification Based on Airborne Lidar Point Cloud with Possibility Method and Multi-Classifier

D Zhao, L Ji, F Yang - Sensors, 2023 - mdpi.com
As important geospatial data, point cloud collected from an aerial laser scanner (ALS)
provides three-dimensional (3D) information for the study of the distribution of typical urban …

Weakly-Supervised Semantic Segmentation of ALS Point Clouds Based on Auxiliary Line and Plane Point Prediction

J Chen, Y Zhang, F Ma, K Huang… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
The segmentation of airborne lidar scanning (ALS) point clouds is one of the basic tasks in
remote sensing field. The existed learning-based methods have acquired satisfactory …