ConDA：基于正则化域拼接的LiDAR分割无监督域自适应
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
AI总结：
提出ConDA框架，通过构建细粒度交互的中间域并结合抗混叠正则化器与熵聚合器进行自训练，显著提升了LiDAR分割的无监督域自适应性能并有效缓解域间差距。
摘要：
将源域学习到的知识迁移到原始目标域以进行无监督域自适应（UDA），对自动驾驶系统的可扩展部署至关重要。UDA中的最先进方法常采用一个核心思路：利用源域和目标域的联合监督信号进行自训练。本文对该思路进行了改进与扩展。我们提出了ConDA，一个基于拼接的LiDAR分割域自适应框架，它：1）构建一个由源域和目标域的细粒度交互信号组成的中间域，且不破坏自车周围物体和背景的语义连贯性；2）利用该中间域进行自训练。为改善源域上的网络训练和中间域上的自训练，我们提出了抗混叠正则化器和熵聚合器，以减少由混叠伪影和噪声伪标签引起的负面影响。通过大量研究，我们证明ConDA在缓解域间差距方面显著优于先前方法。
英文摘要：
Transferring knowledge learned from the labeled source domain to the raw target domain for unsupervised domain adaptation (UDA) is essential to the scalable deployment of autonomous driving systems. State-of-the-art methods in UDA often employ a key idea: utilizing joint supervision signals from both source and target domains for self-training. In this work, we improve and extend this aspect. We present ConDA, a concatenation-based domain adaptation framework for LiDAR segmentation that: 1) constructs an intermediate domain consisting of fine-grained interchange signals from both source and target domains without destabilizing the semantic coherency of objects and background around the ego-vehicle; and 2) utilizes the intermediate domain for self-training. To improve the network training on the source domain and self-training on the intermediate domain, we propose an anti-aliasing regularizer and an entropy aggregator to reduce the negative effect caused by the aliasing artifacts and noisy pseudo labels. Through extensive studies, we demonstrate that ConDA significantly outperforms prior arts in mitigating domain gaps.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
