Cluster-Aware Similarity Diffusion for Instance Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Jifei, Yao, Hantao, Xu, Changsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917883761655808
author Luo, Jifei
Yao, Hantao
Xu, Changsheng
author_facet Luo, Jifei
Yao, Hantao
Xu, Changsheng
contents 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 object re-identification validate the effectiveness of the proposed CAS, our code is publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02343
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cluster-Aware Similarity Diffusion for Instance Retrieval
Luo, Jifei
Yao, Hantao
Xu, Changsheng
Machine Learning
Computer Vision and Pattern Recognition
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 object re-identification validate the effectiveness of the proposed CAS, our code is publicly available.
title Cluster-Aware Similarity Diffusion for Instance Retrieval
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.02343