arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09256cs.CV
收藏

三重感知场景图嵌入

Triplet-Aware Scene Graph Embeddings

University of California, Santa Cruz(加利福尼亚大学圣克鲁兹分校);Intel AI Lab(英特尔人工智能实验室)

Brigit Schroeder, Subarna Tripathi, Hanlin Tang

摘要:

场景图已经成为用于诸如图像生成、视觉关系检测、视觉问答和图像检索等任务的结构化知识的重要形式。虽然可视化和解释词嵌入是很好的理解,场景图嵌入还没有得到充分的探讨。在这项工作中,我们训练场景图嵌入在布局生成任务与不同形式的监督,特别是引入三重监督和数据增强。我们看到,在添加三元组监督和数据增强之后,测量布局预测的良好性的两个指标,即平均交集对并集(mIoU)(52.3%对49.2%)和关系得分(61.7%对54.1%)的性能都有了显着提高。为了理解这些不同的方法如何影响场景图表示,我们应用了几种新的可视化和评估方法来探索场景图嵌入的演变。我们发现,三重监督显着提高嵌入可分性,这是高度相关的布局预测模型的性能。

英文摘要:

Scene graphs have become an important form of structured knowledge for tasks such as for image generation, visual relation detection, visual question answering, and image retrieval. While visualizing and interpreting word embeddings is well understood, scene graph embeddings have not been fully explored. In this work, we train scene graph embeddings in a layout generation task with different forms of supervision, specifically introducing triplet super-vision and data augmentation. We see a significant performance increase in both metrics that measure the goodness of layout prediction, mean intersection-over-union (mIoU)(52.3% vs. 49.2%) and relation score (61.7% vs. 54.1%),after the addition of triplet supervision and data augmentation. To understand how these different methods affect the scene graph representation, we apply several new visualization and evaluation methods to explore the evolution of the scene graph embedding. We find that triplet supervision significantly improves the embedding separability, which is highly correlated with the performance of the layout prediction model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑