DOS: 通过Zipfian原型的可观察软图蒸馏实现自监督点表示
DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation
AI总结：
DOS通过Zipfian原型和可观察点软图蒸馏，提升3D点云自监督学习的语义分割和物体检测性能。
摘要：
最近的自监督学习（SSL）进展展示了在没有人工标注的情况下学习3D点云表示的巨大潜力。然而，由于不规则几何、容易产生捷径的重建和语义分布不平衡，3D点云的SSL仍面临关键挑战。在本文中，我们提出了DOS（Distilling Observable Softmaps），一种新的SSL框架，仅在可观察（未遮蔽）点上自我蒸馏语义相关性软图。这种策略防止了信息从遮蔽区域泄漏，并提供了比离散token-to-prototype分配更丰富的监督。为了解决无监督设置中语义不平衡的挑战，我们引入了Zipfian原型，并通过改进的Sinkhorn-Knopp算法，即Zipf-Sinkhorn，将其纳入其中，该算法在原型使用上施加了幂律先验，并在训练过程中调节目标软图的锐度。DOS在多个基准上均优于当前最先进的方法，在语义分割和3D物体检测任务中，包括nuScenes、Waymo、SemanticKITTI、ScanNet和ScanNet200。无需依赖额外数据或标注，我们的结果表明，可观察点软图蒸馏提供了一种可扩展且有效的学习稳健3D表示的范式。
英文摘要：
Recent advances in self-supervised learning (SSL) have shown tremendous potential for learning 3D point cloud representations without human annotations. However, SSL for 3D point clouds still faces critical challenges due to irregular geometry, shortcut-prone reconstruction, and unbalanced semantics distribution. In this work, we propose DOS (Distilling Observable Softmaps), a novel SSL framework that self-distills semantic relevance softmaps only at observable (unmasked) points. This strategy prevents information leakage from masked regions and provides richer supervision than discrete token-to-prototype assignments. To address the challenge of unbalanced semantics in an unsupervised setting, we introduce Zipfian prototypes and incorporate them using a modified Sinkhorn-Knopp algorithm, Zipf-Sinkhorn, which enforces a power-law prior over prototype usage and modulates the sharpness of the target softmap during training. DOS outperforms current state-of-the-art methods on semantic segmentation and 3D object detection across multiple benchmarks, including nuScenes, Waymo, SemanticKITTI, ScanNet, and ScanNet200, without relying on extra data or annotations. Our results demonstrate that observable-point softmaps distillation offers a scalable and effective paradigm for learning robust 3D representations.
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。
