论文标题
图表编辑距离奖励：学习编辑场景图
Graph Edit Distance Reward: Learning to Edit Scene Graph
论文作者
论文摘要
场景图是弥合语言域和图像域之间差距的重要工具，在诸如VQA之类的跨模式任务中已被广泛采用。在本文中，我们提出了一种根据用户说明编辑场景图的新方法，从未探索过。要具体，为了将编辑场景图作为文本提供的语义，我们提出了一个基于策略梯度和匹配算法的图形编辑距离奖励，以优化神经符号模型。在文本编辑图像检索的背景下，我们验证了我们在CSS和CRIR数据集中方法的有效性。此外，CRIR是我们生成的新合成数据集，我们将尽快发布它以备将来使用。
Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA. In this paper, we propose a new method to edit the scene graph according to the user instructions, which has never been explored. To be specific, in order to learn editing scene graphs as the semantics given by texts, we propose a Graph Edit Distance Reward, which is based on the Policy Gradient and Graph Matching algorithm, to optimize neural symbolic model. In the context of text-editing image retrieval, we validate the effectiveness of our method in CSS and CRIR dataset. Besides, CRIR is a new synthetic dataset generated by us, which we will publish it soon for future use.
