Enhancing Visual Re-ranking Through Denoising Nearest Neighbor Graph Via Continuous CRF

Abstract

Nearest neighbor (NN) graph based visual re-ranking has emerged as a powerful approach for improving retrieval accuracy, offering the advantages of effectively exploring high-dimensional manifolds without requiring additional fine-tuning. However, the effectiveness of NN graph-based re-ranking is fundamentally constrained by the quality of its edge connectivity, as incorrect connections between dissimilar (negative) images frequently occur. This is known as a noisy edge problem, which hinders the re-ranking performance of existing techniques and limits their potential. To remedy this issue, we propose a complementary denoising method based on Continuous Conditional Random Fields (C-CRF) that leverages statistical distances derived from similarity-based distributions. As a pre-processing step for enhancing NN graph-based retrieval, our approach constructs fully connected cliques around each anchor image and employs a novel statistical distance metric to robustly alleviate noisy edges be

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykim2024enhancing

Related papers

• Graph Convolution Based Efficient Re-ranking For Visual Retrieval (2023)9.92
• Understanding Image Retrieval Re-ranking: A Graph Neural Network Perspective (2020)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Contextually Affinitive Neighborhood Refinery For Deep Clustering (2023)2.26
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Neighbor-aware Instance Refining With Noisy Labels For Cross-modal Retrieval (2025)2.26
• Conesep: Cone-based Robust Noise-unlearning Compositional Network For Composed Image Retrieval (2026)0.00
• Visual Re-ranking With Non-visual Side Information (2025)0.00