Image-to-image Retrieval By Learning Similarity Between Scene Graphs

Abstract

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.

Stats

• citations39
• S2 citations—
• github stars0
• HF likes0
• heat score12.02
• arxiv keyyoon2020image

Related papers

• SCENIR: Visual Semantic Clarity Through Unsupervised Scene Graph Retrieval (2025)0.00
• Scene Graph Embeddings Using Relative Similarity Supervision (2021)7.50
• Scene Text Retrieval Via Joint Text Detection And Similarity Learning (2021)16.16
• SPAN: Learning Similarity Between Scene Graphs And Images With Transformers (2023)0.00
• Scene Graph Based Image Retrieval -- A Case Study On The CLEVR Dataset (2019)0.00
• A Deep Local And Global Scene-graph Matching For Image-text Retrieval (2021)10.74
• Through The Prism: Importance-aware Scene Graphs For Image Retrieval (2025)0.00
• Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (2020)17.18