论文标题
RU-NET：场景图生成的正规化展开网络
RU-Net: Regularized Unrolling Network for Scene Graph Generation
论文作者
论文摘要
场景图生成（SGG）旨在检测对象并预测每对对象之间的关系。现有的SGG方法通常遭受多个问题的困扰，包括1）模棱两可的对象表示，因为基于图神经网络的消息传递（GMP）模块通常对虚假节点间的相关性敏感，而2）由于严重的类失衡和大量缺失的注释，关系预测的低多样性。为了解决这两个问题，在本文中，我们提出了一个正规化的展开网络（RU-NET）。我们首先从展开技术的角度研究了GMP和Gragr Laplacian Denoising（GLD）之间的关系，确定GMP可以作为GLD的求解器配制。基于此观察结果，我们提出了一个传开的消息传递模块，并引入了一个基于$ \ ell_p $的图形正则化，以抑制节点之间的虚假连接。其次，我们提出了一个群体多样性增强模块，该模块通过等级最大化促进了关系的预测多样性。系统的实验表明，在各种环境和指标下，RU-NET是有效的。此外，RU-NET在三个流行数据库上实现了新的最新技术：VG，VRD和OI。代码可在https://github.com/siml3/ru-net上找到。
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects. Existing SGG methods usually suffer from several issues, including 1) ambiguous object representations, as graph neural network-based message passing (GMP) modules are typically sensitive to spurious inter-node correlations, and 2) low diversity in relationship predictions due to severe class imbalance and a large number of missing annotations. To address both problems, in this paper, we propose a regularized unrolling network (RU-Net). We first study the relation between GMP and graph Laplacian denoising (GLD) from the perspective of the unrolling technique, determining that GMP can be formulated as a solver for GLD. Based on this observation, we propose an unrolled message passing module and introduce an $\ell_p$-based graph regularization to suppress spurious connections between nodes. Second, we propose a group diversity enhancement module that promotes the prediction diversity of relationships via rank maximization. Systematic experiments demonstrate that RU-Net is effective under a variety of settings and metrics. Furthermore, RU-Net achieves new state-of-the-arts on three popular databases: VG, VRD, and OI. Code is available at https://github.com/siml3/RU-Net.
