旋转不变向量神经元Transformers
VNT-Net: Rotational Invariant Vector Neuron Transformers
摘要:
具有旋转不变性的三维点集学习是机器学习中一个重要而又具有挑战性的问题。通过旋转不变的架构,3D点云神经网络从需要规范的全局姿态和从具有所有可能旋转的穷举数据增强中解脱出来。在这项工作中,我们引入了一个旋转不变的神经网络,结合最近推出的向量神经元与自注意层,建立一个点云向量神经元Transformer网络(VNT-Net)。向量神经元以其在表示SO(3)动作方面的简单性和多功能性而闻名,因此被纳入常见的神经操作中。类似地,Transformer架构已经变得流行,并且最近通过直接应用于图像补丁序列并实现卓越的性能和收敛来成功地用于图像。为了从这两个世界中受益,我们将这两种结构结合起来,主要展示如何调整多头注意力层以符合向量神经元操作。通过这种自适应,注意力层变成SO(3),整个网络变成旋转不变的。实验表明,我们的网络有效地处理任意姿态的3D点云对象。我们还表明,与相关的最先进的方法相比,我们的网络实现了更高的准确性,并且由于常见分类和分割任务中的超参数数量较少,因此需要更少的训练。
英文摘要:
Learning 3D point sets with rotational invariance is an important and challenging problem in machine learning. Through rotational invariant architectures, 3D point cloud neural networks are relieved from requiring a canonical global pose and from exhaustive data augmentation with all possible rotations. In this work, we introduce a rotational invariant neural network by combining recently introduced vector neurons with self-attention layers to build a point cloud vector neuron transformer network (VNT-Net). Vector neurons are known for their simplicity and versatility in representing SO(3) actions and are thereby incorporated in common neural operations. Similarly, Transformer architectures have gained popularity and recently were shown successful for images by applying directly on sequences of image patches and achieving superior performance and convergence. In order to benefit from both worlds, we combine the two structures by mainly showing how to adapt the multi-headed attention layers to comply with vector neurons operations. Through this adaptation attention layers become SO(3) and the overall network becomes rotational invariant. Experiments demonstrate that our network efficiently handles 3D point cloud objects in arbitrary poses. We also show that our network achieves higher accuracy when compared to related state-of-the-art methods and requires less training due to a smaller number of hyperparameters in common classification and segmentation tasks.
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。