论文标题
SPE-NET：通过旋转鲁棒性增强来提高点云分析
SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
论文作者
论文摘要
在本文中，我们提出了一种针对3D Point Cloud Applications量身定制的新型深度建筑，称为SPE-NET。嵌入式``选择性位置编码（SPE）'过程取决于可以有效地处理输入的基础旋转条件的注意机制。然后，这种编码的旋转条件确定要关注网络参数的哪一部分，并显示出有效地帮助降低训练期间优化的自由度。此机制此后可以通过减少训练困难来更好地利用旋转增强，从而使SPE-NET在训练和测试过程中对旋转数据的稳健性。本文中的新发现还敦促我们重新考虑提取的旋转信息与实际测试准确性之间的关系。有趣的是，我们揭示了通过SPE-NET局部编码旋转信息的证据，旋转不变的特征对于在没有任何实际的全局旋转而受益的测试样本中仍然至关重要。我们从经验上证明了SPE-NET的优点以及在四个基准上的相关假设，显示了SOTA方法对旋转和无脊椎测试数据的明显改善。源代码可在https://github.com/zhaofanqiu/spe-net上找到。
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. Such encoded rotation condition then determines which part of the network parameters to be focused on, and is shown to efficiently help reduce the degree of freedom of the optimization during training. This mechanism henceforth can better leverage the rotation augmentations through reduced training difficulties, making SPE-Net robust against rotated data both during training and testing. The new findings in our paper also urge us to rethink the relationship between the extracted rotation information and the actual test accuracy. Intriguingly, we reveal evidences that by locally encoding the rotation information through SPE-Net, the rotation-invariant features are still of critical importance in benefiting the test samples without any actual global rotation. We empirically demonstrate the merits of the SPE-Net and the associated hypothesis on four benchmarks, showing evident improvements on both rotated and unrotated test data over SOTA methods. Source code is available at https://github.com/ZhaofanQiu/SPE-Net.
