Image-to-Image Retrieval by Learning Similarity between Scene Graphs

Authors

  • Sangwoong Yoon Seoul National University
  • Woo Young Kang Kakao Brain
  • Sungwook Jeon Seoul National University
  • SeongEun Lee Seoul National University
  • Changjin Han Seoul National University
  • Jonghun Park Seoul National University
  • Eun-Sol Kim Kakao Brain

Keywords:

Graph-based Machine Learning, Image and Video Retrieval, Language and Vision

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.

Downloads

Published

2021-05-18

How to Cite

Yoon, S., Kang, W. Y., Jeon, S., Lee, S., Han, C., Park, J., & Kim, E.-S. (2021). Image-to-Image Retrieval by Learning Similarity between Scene Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 10718-10726. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17281

Issue

Section

AAAI Technical Track on Machine Learning V