Cluster-aware Similarity Diffusion For Instance Retrieval

Abstract

Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph. However, existing techniques that construct the affinity graph based on pairwise instances can lead to the propagation of misinformation from outliers and other manifolds, resulting in inaccurate results. To overcome this issue, we propose a novel Cluster-Aware Similarity (CAS) diffusion for instance retrieval. The primary concept of CAS is to conduct similarity diffusion within local clusters, which can reduce the influence from other manifolds explicitly. To obtain a symmetrical and smooth similarity matrix, our Bidirectional Similarity Diffusion strategy introduces an inverse constraint term to the optimization objective of local cluster diffusion. Additionally, we have optimized a Neighbor-guided Similarity Smoothing approach to ensure similarity consistency among the local neighbors of each instance. Evaluations in instance retrieval and obj

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyluo2024cluster

Related papers

• Locality Preserving Markovian Transition For Instance Retrieval (2025)0.00
• Efficient Image Retrieval Via Decoupling Diffusion Into Online And Offline Processing (2018)12.25
• AMES: Asymmetric And Memory-efficient Similarity Estimation For Instance-level Retrieval (2024)9.70
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Cross-domain Diffusion With Progressive Alignment For Efficient Adaptive Retrieval (2025)6.34
• Deepdiffusion: Unsupervised Learning Of Retrieval-adapted Representations Via Diffusion-based Ranking On Latent Feature Manifold (2021)5.13
• Ascent Similarity Caching With Approximate Indexes (2021)2.26
• An Efficient Approximate Knn Graph Method For Diffusion On Image Retrieval (2019)6.34