Paper Info
Title
DFAN: Dual-Branch Feature Alignment Network for Domain Adaptation on Point Clouds
Abstract
Unsupervised domain adaptation (UDA) significantly reduces the gap between the source domain and the target domain in machine learning and computer vision tasks. Most UDA approaches are applied to images and videos, and only a few methods implement domain adaptation on 3-D computer vision problems. The existing UDA approaches operating on point clouds try to extract domain-invariant features in different domains for feature alignment. However, higher commonality brings less diversity and results a loss of detailed information. In this article, we propose a novel dual-branch feature alignment network (DFAN) architecture for domain adaptation on point cloud visual tasks to better exploit the respective characteristics of local and global features. Our approach specializes in the extraction and alignment of global and local features with different strategies in each branch to complement each other. We also introduce a hierarchical alignment strategy for local feature alignment and a distribution alignment strategy for global feature alignment. Experiments on the PointDA-10 and PointSegDA datasets show that our approach achieves state-of-the-art performance on the UDA of point cloud classification and segmentation tasks. The ablation study demonstrates the effectiveness of the dual-branch design and the feature alignment strategies.
Year
DOI
Venue
2022
10.1109/TGRS.2022.3171038
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Keywords
DocType
Volume
Feature extraction, Point cloud compression, Task analysis, Three-dimensional displays, Computer vision, Adaptation models, Deep learning, 3-D computer vision, domain adaptation, point cloud classification, point cloud segmentation
Journal
60
ISSN
Citations 
PageRank 
0196-2892
0
0.34
References 
Authors
0
5
Name
Order
Citations
PageRank
Liangwei Shi100.34
Zhimin Yuan201.01
Ming Cheng35413.93
Yiping Chen4167.69
Cheng Wang521832.63