IEEE Trans Cybern. 2018 Jan;48(1):412-422. doi: 10.1109/TCYB.2016.2638924. Epub 2016 Dec 28.
Effective 3-D shape retrieval is an important problem in 3-D shape analysis. Recently, feature learning-based shape retrieval methods have been widely studied, where the distance metrics between 3-D shape descriptors are usually hand-crafted. In this paper, motivated by the fact that deep neural network has the good ability to model nonlinearity, we propose to learn an effective nonlinear distance metric between 3-D shape descriptors for retrieval. First, the locality-constrained linear coding method is employed to encode each vertex on the shape and the encoding coefficient histogram is formed as the global 3-D shape descriptor to represent the shape. Then, a novel deep metric network is proposed to learn a nonlinear transformation to map the 3-D shape descriptors to a nonlinear feature space. The proposed deep metric network minimizes a discriminative loss function that can enforce the similarity between a pair of samples from the same class to be small and the similarity between a pair of samples from different classes to be large. Finally, the distance between the outputs of the metric network is used as the similarity for shape retrieval. The proposed method is evaluated on the McGill, SHREC'10 ShapeGoogle, and SHREC'14 Human shape datasets. Experimental results on the three datasets validate the effectiveness of the proposed method.
有效的 3D 形状检索是 3D 形状分析中的一个重要问题。最近，基于特征学习的形状检索方法得到了广泛的研究，其中 3D 形状描述符之间的距离度量通常是手工制作的。在本文中，受深度神经网络具有良好的建模非线性能力的启发，我们提出学习用于检索的 3D 形状描述符之间的有效非线性距离度量。首先，采用局部约束线性编码方法对形状上的每个顶点进行编码，并形成编码系数直方图作为全局 3D 形状描述符来表示形状。然后，提出了一种新颖的深度度量网络来学习非线性变换，将 3D 形状描述符映射到非线性特征空间。所提出的深度度量网络最小化判别损失函数，该函数可以强制来自同一类别的一对样本之间的相似性较小，而来自不同类别的一对样本之间的相似性较大。最后，将度量网络的输出之间的距离用作形状检索的相似性。在 McGill、SHREC'10 ShapeGoogle 和 SHREC'14 Human 形状数据集上对所提出的方法进行了评估。三个数据集上的实验结果验证了所提出方法的有效性。
