arXiv 2406.167762024-06-24cs.CV

面向半监督3D实例分割的实例一致性正则化

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）

Yizheng Wu, Zhiyu Pan, Kewei Wang, Xingyi Li, Jiahao Cui, Liwen Xiao, Guosheng Lin, Zhiguo Cao

备注：: 14 pages, 10 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对半监督3D实例分割中语义伪标签噪声导致自训练崩溃的问题，提出基于纯实例知识的InsTeacher3D网络与DKNet模型，通过实例一致性正则化生成高质量伪标签，性能显著超越现有半监督最优方法。

摘要：

带有逐点语义和实例标签的大规模数据集对3D实例分割至关重要，但标注成本高昂。为利用未标注数据，以往的半监督3D实例分割方法探索了自训练框架，这类框架依赖高质量伪标签实现一致性正则化，它们直观地以联合学习方式同时使用实例和语义伪标签。然而，语义伪标签中存在大量噪声，这些噪声源于类别分布不均衡以及相似但不同类别间的天然混淆，会导致自训练过程出现严重崩溃。受3D实例互不重叠且空间可分离这一观察的启发，我们探究能否仅依靠实例一致性正则化来提升半监督分割性能。为此，我们提出了一种新型自训练网络InsTeacher3D，用于挖掘和利用未标注数据中的纯实例知识。我们首先构建了一个并行的基础3D实例分割模型DKNet，该模型通过判别性实例核区分每个实例，无需依赖语义分割。基于DKNet，我们进一步设计了一种新型实例一致性正则化框架，用于生成并利用高质量实例伪标签。在多个大规模数据集上的实验结果表明，InsTeacher3D的性能显著优于现有的半监督SOTA（state-of-the-art，当前最优）方法。代码可在以下地址获取：https://github.com/W1zheng/InsTeacher3D。

英文摘要：

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://github.com/W1zheng/InsTeacher3D.

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。