论文标题
图像到图像通过学习场景图之间的相似性来检索
Image-to-Image Retrieval by Learning Similarity between Scene Graphs
论文作者
论文摘要
当场景图以结构化和象征性的方式紧凑地汇总了图像的高级内容，两个图像的场景图之间的相似性反映了其内容的相关性。基于这个想法，我们使用图形神经网络测量的场景图相似性提出了一种新颖的图像到图像检索方法。在我们的方法中，训练了图形神经网络，以预测使用预先训练的句子相似性模型从人类通知字幕计算的代理图像相关性度量。我们收集并发布数据集，以通过人类注释者测量的图像相关性来评估检索算法。收集到的数据集表明，与其他竞争基线相比，我们的方法与人类对图像相似性的看法非常吻合。
As a scene graph compactly summarizes the high-level content of an image in a structured and symbolic manner, the similarity between scene graphs of two images reflects the relevance of their contents. Based on this idea, we propose a novel approach for image-to-image retrieval using scene graph similarity measured by graph neural networks. In our approach, graph neural networks are trained to predict the proxy image relevance measure, computed from human-annotated captions using a pre-trained sentence similarity model. We collect and publish the dataset for image relevance measured by human annotators to evaluate retrieval algorithms. The collected dataset shows that our method agrees well with the human perception of image similarity than other competitive baselines.
