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 online: this https URL

本研究提出了一种名为 Correlation Verification Networks (CVNet) 的图像检索网络，包括深度堆叠的 4D 卷积层，以及横跨多个尺度的特征金字塔和特征相关结构，并使用课程学习与硬负采样和 “捉迷藏” 策略处理困难样本，其表现优于现有方法 (+12.6% in mAP on ROxford-Hard+1M set)。