Correlation Verification For Image Retrieval

Abstract

Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network, comprising deeply stacked 4D convolutional layers, gradually compresses dense feature correlation into image similarity while learning diverse geometric matching patterns from various image pairs. To enable cross-scale matching, it builds feature pyramids and constructs cross-scale feature correlations within a single inference, replacing costly multi-scale inferences. In addition, we use curriculum learning with the hard negative mining and Hide-and-Seek strategy to handle hard samples without losing generality. Our proposed re-ranking network shows state-of-the-art performance on several retrieval benchmarks with a significant margin (+12.6% in mAP on ROxford-Hard+1M set) over state-of-the-art methods. The source code and models are available onli

Stats

• citations78
• S2 citations—
• github stars191
• HF likes0
• heat score18.80
• arxiv keylee2022correlation

Related papers

• Geometric Image Correspondence Verification By Dense Pixel Matching (2019)7.16
• Graph Convolution Based Efficient Re-ranking For Visual Retrieval (2023)9.92
• Moving Towards Centers: Re-ranking With Attention And Memory For Re-identification (2021)8.09
• Visual Model Checking: Graph-based Inference Of Visual Routines For Image Retrieval (2026)0.00
• Differential Geometric Retrieval Of Deep Features (2017)2.26
• Understanding Image Retrieval Re-ranking: A Graph Neural Network Perspective (2020)0.00
• Spectral Geometric Verification: Re-ranking Point Cloud Retrieval For Metric Localization (2022)14.60
• Dynamic Spatial Verification For Large-scale Object-level Image Retrieval (2019)0.00