具有稀疏且非均匀标注的点云语义分割
Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations
AI总结：
针对点云语义分割中稀疏标注的非均匀性问题，提出AADNet网络，通过标签感知下采样和乘性动态熵梯度校准，在多种标签率下实现性能提升。
摘要：
利用均匀分布的稀疏标注，弱监督学习缓解了点云语义分割任务中对细粒度标注的严重依赖。然而，尽管稀疏标注的非均匀性在现实场景中很常见，却鲜有工作对此进行讨论。因此，本工作将概率密度函数引入梯度采样近似方法中，以定性分析弱监督学习下标注稀疏性和非均匀性的影响。基于我们的分析，我们提出了一种自适应标注分布网络（AADNet），能够在任意分布的稀疏标注上进行鲁棒学习。具体而言，我们提出了一种标签感知的点云下采样策略，以增加训练阶段中涉及的标注比例。此外，我们设计了乘性动态熵作为梯度校准函数，以缓解由非均匀分布的稀疏标注引起的梯度偏差，并显式地减少认知不确定性。在没有任何先验限制和额外信息的情况下，我们提出的方法在多种标签率和不同标注分布下实现了全面的性能提升。
英文摘要：
Utilizing uniformly distributed sparse annotations, weakly supervised learning alleviates the heavy reliance on fine-grained annotations in point cloud semantic segmentation tasks. However, few works discuss the inhomogeneity of sparse annotations, albeit it is common in real-world scenarios. Therefore, this work introduces the probability density function into the gradient sampling approximation method to qualitatively analyze the impact of annotation sparsity and inhomogeneity under weakly supervised learning. Based on our analysis, we propose an Adaptive Annotation Distribution Network (AADNet) capable of robust learning on arbitrarily distributed sparse annotations. Specifically, we propose a label-aware point cloud downsampling strategy to increase the proportion of annotations involved in the training stage. Furthermore, we design the multiplicative dynamic entropy as the gradient calibration function to mitigate the gradient bias caused by non-uniformly distributed sparse annotations and explicitly reduce the epistemic uncertainty. Without any prior restrictions and additional information, our proposed method achieves comprehensive performance improvements at multiple label rates and different annotation distributions.
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。
