Attentive Relational Networks for Mapping Images to Scene Graphs
This addresses the problem of inferring complex contextual relationships in images for applications like visual understanding, but it appears incremental as it builds on existing object detection and relational modeling techniques.
The authors tackled scene graph generation by proposing an Attentive Relational Network with semantic transformation and graph self-attention modules, achieving effective results on the Visual Genome Dataset.
Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object detection using deep learning techniques, inferring complex contextual relationships and structured graph representations from visual data remains a challenging topic. In this study, we propose a novel Attentive Relational Network that consists of two key modules with an object detection backbone to approach this problem. The first module is a semantic transformation module utilized to capture semantic embedded relation features, by translating visual features and linguistic features into a common semantic space. The other module is a graph self-attention module introduced to embed a joint graph representation through assigning various importance weights to neighboring nodes. Finally, accurate scene graphs are produced by the relation inference module to recognize all entities and the corresponding relations. We evaluate our proposed method on the widely-adopted Visual Genome Dataset, and the results demonstrate the effectiveness and superiority of our model.