Chauhan Vikas, Tiwari Aruna, Venkata Boppudi, Naik Vislavath
Discipline of Computer Science and Engineering, Indian Institute of Technology, Indore, India.
Evol Syst (Berl). 2022 Sep 7:1-11. doi: 10.1007/s12530-022-09463-z.
The importance of the graphical convolution network in multi-label classification has grown in recent years due to its label embedding representation capabilities. The graphical convolution network is able to capture the label dependencies using the correlation between labels. However, the graphical convolution network suffers from an over-smoothing problem when the layers are increased in the network. Over-smoothing makes the nodes indistinguishable in the deep graphical convolution network. This paper proposes a normalization technique to tackle the over-smoothing problem in the graphical convolution network for multi-label classification. The proposed approach is an efficient multi-label object classifier based on a graphical convolution neural network that tackles the over-smoothing problem. The proposed approach normalizes the output of the graph such that the total pairwise squared distance between nodes remains the same after performing the convolution operation. The proposed approach outperforms the existing state-of-the-art approaches based on the results obtained from the experiments performed on MS-COCO and VOC2007 datasets. The experimentation results show that pairnorm mitigates the effect of over-smoothing in the case of using a deep graphical convolution network.
近年来，由于其标签嵌入表示能力，图形卷积网络在多标签分类中的重要性日益增加。图形卷积网络能够利用标签之间的相关性来捕捉标签依赖性。然而，当网络层数增加时，图形卷积网络会出现过平滑问题。过平滑使得深度图形卷积网络中的节点难以区分。本文提出一种归一化技术来解决图形卷积网络在多标签分类中的过平滑问题。所提出的方法是一种基于图形卷积神经网络的高效多标签对象分类器，可解决过平滑问题。所提出的方法对图的输出进行归一化，使得在执行卷积操作后节点之间的总成对平方距离保持不变。基于在MS-COCO和VOC2007数据集上进行的实验结果，所提出的方法优于现有的最先进方法。实验结果表明，在使用深度图形卷积网络的情况下，pairnorm减轻了过平滑的影响。
