发表机构
Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TC-ADA提出一次性主动域适应方法，结合视觉基础模型与无监督适应选择目标图像，并联合校准源与目标监督，在少量标注下显著提升语义分割性能。
AI 中文摘要
手动密集标注仍然是阻碍语义分割模型在新驾驶环境中部署的主要障碍。主动域适应（ADA）通过仅标注目标域的选定部分来实现标签高效迁移。现有的ADA方法通常通过多轮采集、标注和重训练来实现这一过程。我们研究了一种实用的一次性图像级设置，该设置在单轮中选定并密集标注固定的目标子集，然后进行不间断的适应。在此设置中，我们开发了目标校准主动域适应（TC-ADA），作为完整图像采集和目标校准适应的联合设计。阶段1使用视觉基础模型（VFM）的视觉表示以及固定无监督域适应模型的语义预测，在无目标标注的情况下选择具有代表性和信息量的目标图像。阶段2联合使用有标签源数据、有标签目标数据和剩余的无标签目标数据，同时校准源和目标监督在有限目标标签下的权重。在五个合成到真实和真实到真实的驾驶迁移实验中，TC-ADA相较于代表性的ADA基线表现出持续改进。在四个迁移中仅使用23至46张有标签目标图像，在Mapillary上使用140张，TC-ADA与仅使用目标数据的全监督相比，平均交并比（mIoU）差距保持在1.9个百分点以内。代码将在此https URL提供。
英文摘要
Manual dense annotation remains a major obstacle to deploying semantic segmentation models in new driving environments. Active domain adaptation (ADA) seeks label-efficient transfer by annotating only a selected portion of the target domain. Existing ADA methods commonly implement this process through multiple rounds of acquisition, annotation, and retraining. We study a practical one-shot image-level setting that selects and densely annotates a fixed target subset in a single round, followed by uninterrupted adaptation. Within this setting, we develop Target-Calibrated Active Domain Adaptation (TC-ADA) as a joint design of complete-image acquisition and target-calibrated adaptation. Stage~1 uses visual representations from a vision foundation model (VFM) together with semantic predictions from a fixed unsupervised domain adaptation model to select representative and informative target images without target annotations. Stage~2 jointly uses labeled source data, labeled target data, and the remaining unlabeled target data, while calibrating source and target supervision under limited target labels. Extensive experiments across five synthetic-to-real and real-to-real driving transfers show consistent improvements over representative ADA baselines. With only 23 to 46 labeled target images on four transfers and 140 on Mapillary, TC-ADA stays within 1.9 mean intersection over union (mIoU) points of target-only full supervision. Code will be available at https://github.com/ywher/TC-ADA.
Comments13 pages, 15 tables, 3 figures
