文件名称：Knowledge-Embedded Routing Network for Scene Graph Generation.pdf
文件大小：1.23MB
文件格式：PDF
更新时间：2022-08-29 09:00:43
KG
To understand a scene in depth not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them. However, sincethedistributionofreal-worldrelationshipsisseriously unbalanced, existing methods perform quite poorly forthelessfrequentrelationships. Inthiswork,wefindthat the statistical correlations between object pairs and their relationships can effectively regularize semantic space and make prediction less ambiguous, and thus well address the unbalanced distribution issue. To achieve this, we incorporate these statistical correlations into deep neural networks to facilitate scene graph generation by developing a Knowledge-Embedded Routing Network. More specifically, weshowthatthestatisticalcorrelationsbetweenobjectsappearing in images and their relationships, can be explicitly representedbyastructuredknowledgegraph,andarouting mechanism is learned to propagate messages through the graph to explore their interactions. Extensive experiments on the large-scale Visual Genome dataset demonstrate the superiority of the proposed method over current state-ofthe-art competitors.