Graph Edit Distance Reward: Learning to Edit Scene Graph
Scene Graph, as a vital tool to bridge the gap between the 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, based on the Policy Gradient and Graph Matching algorithm, we propose a Graph Edit Distance Reward to optimize neural symbolic model, in order to learn editing scene graphs as the semantics given by texts. 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, and we will publish it soon for future use."