边缘上的魔鬼：用于场景图生成的选择性四元注意力
Devil's on the Edges: Selective Quad Attention for Scene Graph Generation
AI总结：
针对场景图生成中无关物体和候选关系的干扰问题，提出SQUAT网络，通过边缘选择模块筛选相关物体对并利用四元注意力更新特征，在Visual Genome和Open Images v6基准上达到最先进水平。
摘要：
场景图生成旨在从图像中构建语义图结构，使得其节点和边缘分别表示物体及其关系。该任务的主要挑战之一在于图像中存在干扰物体和关系；上下文推理受到无关物体或背景的强烈干扰，更重要的是，受到大量无关候选关系的强烈干扰。为解决此问题，我们提出了选择性四元注意力网络（SQUAT），该网络学习选择相关的物体对，并通过多样的上下文交互对其进行消歧。SQUAT包含两个主要组件：边缘选择和四元注意力。边缘选择模块选择相关的物体对，即场景图中的边缘，这有助于上下文推理，随后四元注意力模块使用边缘到节点和边缘到边缘的交叉注意力来更新边缘特征，以捕捉物体与物体对之间的上下文信息。实验证明了SQUAT的强大性能和鲁棒性，在Visual Genome和Open Images v6基准上达到了最先进水平。
英文摘要：
Scene graph generation aims to construct a semantic graph structure from an image such that its nodes and edges respectively represent objects and their relationships. One of the major challenges for the task lies in the presence of distracting objects and relationships in images; contextual reasoning is strongly distracted by irrelevant objects or backgrounds and, more importantly, a vast number of irrelevant candidate relations. To tackle the issue, we propose the Selective Quad Attention Network (SQUAT) that learns to select relevant object pairs and disambiguate them via diverse contextual interactions. SQUAT consists of two main components: edge selection and quad attention. The edge selection module selects relevant object pairs, i.e., edges in the scene graph, which helps contextual reasoning, and the quad attention module then updates the edge features using both edge-to-node and edge-to-edge cross-attentions to capture contextual information between objects and object pairs. Experiments demonstrate the strong performance and robustness of SQUAT, achieving the state of the art on the Visual Genome and Open Images v6 benchmarks.
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。
