Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing


  • Fan Yang The University of Tokyo
  • Ryota Hinami The University of Tokyo
  • Yusuke Matsui National Institute of Informatics
  • Steven Ly University of Southern California
  • Shin’ichi Satoh National Institute of Informatics




Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years. A downside to diffusion is that it performs slowly in comparison to the naive k-NN search, which causes a non-trivial online computational cost on large datasets. To overcome this weakness, we propose a novel diffusion technique in this paper. In our work, instead of applying diffusion to the query, we precompute the diffusion results of each element in the database, making the online search a simple linear combination on top of the k-NN search process. Our proposed method becomes 10∼ times faster in terms of online search speed. Moreover, we propose to use late truncation instead of early truncation in previous works to achieve better retrieval performance.




How to Cite

Yang, F., Hinami, R., Matsui, Y., Ly, S., & Satoh, S. (2019). Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9087-9094. https://doi.org/10.1609/aaai.v33i01.33019087



AAAI Technical Track: Vision