Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing Transformer-based methods either employ distinct queries for objects and predicates or utilize holistic queries for relation triplets and hence often suffer from limited capacity in learning low-frequency relationships. In this paper, we present a new Transformer-based method, called DSGG, that views scene graph detection as a direct graph prediction problem based on a unique set of graph-aware queries. In particular, each graph-aware query encodes a compact representation of both the node and all of its relations in the graph, acquired through the utilization of a relaxed sub-graph matching during the training process. Moreover, to address the problem of relational semantic overlap, we utilize a strategy for relation distillation, aiming to efficiently learn multiple instances of semantic relationships. Extensive experiments on the VG and the PSG datasets show that our model achieves state-of-the-art results, showing a significant improvement of 3.5\% and 6.7\% in mR@50 and mR@100 for the scene-graph generation task and achieves an even more substantial improvement of 8.5\% and 10.3\% in mR@50 and mR@100 for the panoptic scene graph generation task. Code is available at \url{https://github.com/zeeshanhayder/DSGG}.

本文介绍了一种新的基于Transformer的方法，称为DSGG，将场景图检测视为基于一组独特的图感知查询的直接图预测问题，并采用放松子图匹配的方式获取图节点及其关系的紧凑表示，以及通过关系蒸馏策略来解决关系语义重叠问题。实验结果表明，该模型在场景图生成任务上取得了最先进的结果，在mR@50和mR@100方面分别取得了3.5％和6.7％的显著改进，在全景场景图生成任务上甚至取得了8.5％和10.3％的更大改进。

DSGG：稠密关系变换器用于端到端场景图生成