In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source domain) and testing (target domain) data originate from different LiDAR sensors. To overcome this shortcoming, we propose an unsupervised domain adaptation framework that leverages unlabeled target domain data for self-supervision, coupled with an unpaired mask transfer strategy to mitigate the impact of domain shifts. Furthermore, we introduce gated adapter modules with a small number of parameters into the network to account for target domain-specific information. Experiments adapting from both real-to-real and synthetic-to-real LiDAR semantic segmentation benchmarks demonstrate the significant improvement over prior arts.
翻译:在本文中,我们侧重于在LiDAR 语义分割法中较少探索、但更现实和复杂的域适应问题。当培训(源域)和测试(目标域)数据来自不同的LiDAR传感器时,现有区块模型的性能显著下降。为了克服这一缺陷,我们建议建立一个不受监督的域块适应框架,利用无标签目标域数据进行自我监督,并辅之以一个无标签的遮罩传输战略,以减轻域转移的影响。此外,我们还在网络中引入了带少量参数的锁定适配器模块,以计算特定域信息。从真实到真实和合成到真实的LiDAR 语义分割基准进行的实验表明比以前的艺术有了重大改进。