Fast Spectral Ranking For Similarity Search

Abstract

Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 10^5 images, the offline cost is only a few hours, while query time is comparable to standard similarity search.

Stats

• citations34
• S2 citations—
• github stars0
• HF likes0
• heat score11.58
• arxiv keyiscen2017fast

Related papers

• Hybrid Diffusion: Spectral-temporal Graph Filtering For Manifold Ranking (2018)2.26
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Adaptive Prefiltering For High-dimensional Similarity Search: A Frequency-aware Approach (2025)0.00
• Differential Geometric Retrieval Of Deep Features (2017)2.26
• Spatially Optimized Compact Deep Metric Learning Model For Similarity Search (2024)0.00
• Learning Deep Similarity Models With Focus Ranking For Fabric Image Retrieval (2017)11.58
• Image Retrieval Methods In The Dissimilarity Space (2024)0.00
• Sketches Image Analysis: Web Image Search Engine Usinglsh Index And DNN Inceptionv3 (2021)0.00