Efficient Image Retrieval Via Decoupling Diffusion Into Online And Offline Processing

Abstract

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.

Stats

• citations42
• S2 citations—
• github stars0
• HF likes0
• heat score12.25
• arxiv keyyang2018efficient

Related papers

• An Efficient Approximate Knn Graph Method For Diffusion On Image Retrieval (2019)6.34
• Efficient Diffusion On Region Manifolds: Recovering Small Objects With Compact CNN Representations (2016)15.83
• Accurate And Fast Pixel Retrieval With Spatial And Uncertainty Aware Hypergraph Diffusion (2024)0.00
• Bloom Filters And Compact Hash Codes For Efficient And Distributed Image Retrieval (2016)6.34
• Deepdiffusion: Unsupervised Learning Of Retrieval-adapted Representations Via Diffusion-based Ranking On Latent Feature Manifold (2021)5.13
• Cluster-aware Similarity Diffusion For Instance Retrieval (2024)0.00
• Genetic Algorithms For The Optimization Of Diffusion Parameters In Content-based Image Retrieval (2019)9.23
• Hybrid Diffusion: Spectral-temporal Graph Filtering For Manifold Ranking (2018)2.26