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.
Cite
Text
Yoon et al. "Image-to-Image Retrieval by Learning Similarity Between Scene Graphs." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I12.17281Markdown
[Yoon et al. "Image-to-Image Retrieval by Learning Similarity Between Scene Graphs." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/yoon2021aaai-image/) doi:10.1609/AAAI.V35I12.17281BibTeX
@inproceedings{yoon2021aaai-image,
title = {{Image-to-Image Retrieval by Learning Similarity Between Scene Graphs}},
author = {Yoon, Sangwoong and Kang, Woo-Young and Jeon, Sungwook and Lee, SeongEun and Han, Changjin and Park, Jonghun and Kim, Eun-Sol},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {10718-10726},
doi = {10.1609/AAAI.V35I12.17281},
url = {https://mlanthology.org/aaai/2021/yoon2021aaai-image/}
}