Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

TL;DR

This paper introduces a hybrid spectral-temporal graph filtering method for manifold ranking in image retrieval, balancing computational speed and memory efficiency while maintaining state-of-the-art accuracy.

Contribution

A novel hybrid filtering approach that combines spectral and temporal methods, offering a controllable trade-off between space and time complexity.

Findings

Achieves retrieval performance comparable to state-of-the-art methods.

Reduces memory requirements compared to spectral filtering.

Faster query times than purely temporal filtering.

Abstract

State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founded hybrid filtering approach allowing full control of the space-time trade-off between these two extremes. Experimentally, we verify that our hybrid method delivers results on par with the state of the art, with lower memory demands compared to spectral filtering approaches and faster compared to temporal filtering.