Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
This addresses efficiency bottlenecks for large-scale image retrieval systems, though it appears incremental as it optimizes an existing diffusion framework.
The paper tackles the slow online computational cost of diffusion-based image retrieval by decoupling diffusion into offline pre-computation and online linear combination, achieving 10× faster online search speed while improving retrieval performance through late truncation.
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 pre-compute 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.