基于场景先验知识的场景图生成模型

打开文本图片集

中图分类号：TP391 文献标志码：A

Abstract： Scene Graph Generation technology still has a predicate prediction long-tailed distribution and unreasonable prediction problems， therefore，a scene-assisted scene graph generation（SA） model was proposed. Under the Faster R-CNN framework，scene prior knowledge was introduced and combined with image visual features. Scene category inference and predicate prediction were performed through a dual-branch structure. Experimental results demonstrate that the SA model performs effectively in predicate classification and scene graph detection tasks. Compared with traditional models， predicate classification accuracy improves by 4 percentage points，and scene graph detection accuracy increases by O.8 percentage points. Ablation experiments confirm that the dual-branch module effectively enhances model performance.

Keywords： scene graph generation； prior knowledge；object detection;deep learning

场景图生成技术[1]是一种强大的场景理解工具，利用图形结构化表示辅助理解图像内容，在视觉问答、自动驾驶的环境理解以及图像内容检索等应用中有重要作用。（剩余9101字）