State-of-the-art 3D semantic segmentation models are trained on the off-the-shelf public benchmarks, but they often face the major challenge when these well-trained models are deployed to a new domain. In this paper, we propose an Active-and-Adaptive Segmentation (ADAS) baseline to enhance the weak cross-domain generalization ability of a well-trained 3D segmentation model, and bridge the point distribution gap between domains. Specifically, before the cross-domain adaptation stage begins, ADAS performs an active sampling operation to select a maximally-informative subset from both source and target domains for effective adaptation, reducing the adaptation difficulty under 3D scenarios. Benefiting from the rise of multi-modal 2D-3D datasets, ADAS utilizes a cross-modal attention-based feature fusion module that can extract a representative pair of image features and point features to achieve a bi-directional image-point feature interaction for better safe adaptation. Experimentally, ADAS is verified to be effective in many cross-domain settings including: 1) Unsupervised Domain Adaptation (UDA), which means that all samples from target domain are unlabeled; 2) Unsupervised Few-shot Domain Adaptation (UFDA) which means that only a few unlabeled samples are available in the unlabeled target domain; 3) Active Domain Adaptation (ADA) which means that the selected target samples by ADAS are manually annotated. Their results demonstrate that ADAS achieves a significant accuracy gain by easily coupling ADAS with self-training methods or off-the-shelf UDA works.
翻译:高级 3D 语义分解 模型 以现成的公开基准为标准, 接受 最新 3D 语义分解 模型 培训, 但这些经过良好训练的模型被部署到新领域时, 往往面临重大挑战 。 在本文件中, 我们建议 使用 积极 和 适应 分解 (ADS) 基线, 以强化训练有素 3D 分解 模型的薄弱跨部通用能力, 并缩小各域之间的点分布差距 。 具体地说, 在跨部适应阶段开始之前, ADAS 进行积极的抽样作业, 从源和目标域中选择一个最大程度的强化子集, 以有效适应为目的, 减少 3DA 情景下的精确度困难。 由于多模式 2 DADA 数据集的上升, ADAS 使用一个跨模式基于关注的跨模式集成模块, 以双向图像点特征互动, 以更安全地适应为目的。 实验性地, AADAS 进行快速的验证, 在许多跨部环境环境中都有效, 包括:1) 不可监视的 DoVADADA (UDA) 的 标称 一个目标域, 这意味着所有标值的标值的标值的标值的标定的标定的标定 。 DoDADADADADAD 2 。