Understanding Image Retrieval Re-ranking: A Graph Neural Network Perspective

Abstract

The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high computational complexity, which leads to an unaffordable time cost for real-world applications. In this paper, we revisit re-ranking and demonstrate that re-ranking can be reformulated as a high-parallelism Graph Neural Network (GNN) function. In particular, we divide the conventional re-ranking process into two phases, i.e., retrieving high-quality gallery samples and updating features. We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph. In practice, GNN only needs to concern vertices with the connected edges. Since the graph is sparse, we can efficiently update the vertex features. On the Market-1501 dataset, we accelerate the re-ranking processi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2020understanding

Related papers

• Graph Convolution Based Efficient Re-ranking For Visual Retrieval (2023)9.92
• Enhancing Visual Re-ranking Through Denoising Nearest Neighbor Graph Via Continuous CRF (2024)0.00
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• GUITAR: Gradient Pruning Toward Fast Neural Ranking (2023)2.26
• Moving Towards Centers: Re-ranking With Attention And Memory For Re-identification (2021)8.09
• Chain-of-thought Re-ranking For Image Retrieval Tasks (2025)1.81
• Re-ranking Person Re-identification With K-reciprocal Encoding (2017)23.09
• Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00