arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.05548cs.CV
收藏

三维点云特征转换的几何方法

3D Point Cloud Feature Explanations Using Gradient-Based Methods

The University of Manchester(曼彻斯特大学)

Ananya Gupta, Simon Watson, Hujun Yin

摘要:

可解释性是推动用户信任使用神经网络执行具有实质影响的任务的重要因素。然而,在这一领域所做的大部分工作都集中在图像分析上,而没有考虑到3D数据。我们扩展的显着性方法,已被证明是对图像数据处理3D数据。我们分析了点云和体素空间中的特征,并表明3D数据中的边缘和拐角被认为是重要的特征,而平面表面被认为不太重要。该方法是模型不可知的,可以提供有用的信息学习功能。在3D数据本质上是稀疏的这一认识的驱动下,我们可视化了基于体素的分类网络所学习的特征,并表明这些特征也是稀疏的,可以相对容易地修剪,从而产生更有效的神经网络。我们的研究结果表明,Voxception-ResNet模型可以被修剪到其参数的5%,而精度损失可以忽略不计。

英文摘要:

Explainability is an important factor to drive user trust in the use of neural networks for tasks with material impact. However, most of the work done in this area focuses on image analysis and does not take into account 3D data. We extend the saliency methods that have been shown to work on image data to deal with 3D data. We analyse the features in point clouds and voxel spaces and show that edges and corners in 3D data are deemed as important features while planar surfaces are deemed less important. The approach is model-agnostic and can provide useful information about learnt features. Driven by the insight that 3D data is inherently sparse, we visualise the features learnt by a voxel-based classification network and show that these features are also sparse and can be pruned relatively easily, leading to more efficient neural networks. Our results show that the Voxception-ResNet model can be pruned down to 5\% of its parameters with negligible loss in accuracy.

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。

↑