发表机构
School of Artificial Intelligence, Nanyang Normal University; School of Computer Science and Engineering, Northeastern University; Fujian Key Laboratory of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University（南阳师范学院人工智能学院; 东北大学计算机科学与工程学院; 厦门大学信息学院福建省智慧城市感知与计算重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究3D无监督域自适应分割，提出CVKD-UDA方法，通过将体素大小作为核心因素构建域相似表示，利用跨视图互补线索及设计相关组件平衡热身模型特性，有效提升自训练方法性能，为3D UDA分割提供新视角。
AI 中文摘要
3D无监督域自适应（UDA）分割可降低新域数据手动标注的高成本。自训练已成为该领域的主导方法，其成功很大程度上依赖于初始化良好的热身模型来生成可靠的伪标签。然而，现有方法常依赖源监督或输出级对抗对齐来获取热身模型，因域间差距大而泛化受限且训练不稳定。构建域相似表示是弥合差距的有效方法。本文提出CVKD-UDA，将体素大小作为核心设计因素来构建域相似表示，并利用跨视图互补线索平衡热身模型的可迁移性和可辨别性。首先，通过改变体素大小生成两个互补视图并引入跨视图知识蒸馏以增强模型的泛化和目标感知。其次，为平衡可迁移性和可辨别性，设计了轻量级解耦适配器和辅助模仿分类器来解耦跨视图知识转移。在两个基准上的大量实验表明，CVKD-UDA有效提高了自训练方法的性能，并为3D UDA分割提供了新视角。代码将在GitHub上提供。
英文摘要
3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pseudo labels. However, existing methods often depend on source supervision or output-level adversarial alignment to obtain the warm-up model, which suffer from limited generalization and training instability due to the large domain gap between domains. Constructing domain-similar representations is an effective way to bridge this gap. In this work, we propose CVKD-UDA, which revisits voxel size as a core design factor to construct domain-similar representations and leverages cross-view complementary cues to balance transferability and discriminability of the warm-up model. First, we generate two complementary views by varying voxel sizes and introduce a cross-view knowledge distillation (CVKD) to enhance generalization and target perception of the model. Second, to balance transferability and discriminability, we design a lightweight Decouple-Adapter and an auxiliary imitation classifier to decouple cross-view knowledge transfer. Extensive experiments on two benchmarks demonstrate that CVKD-UDA effectively improves the performance of self-training methods and provides a new perspective for 3D UDA segmentation. Our code will be available at GitHub.
