Correlation Verification for Image Retrieval

Seongwon Lee, Hongje Seong, Suhyeon Lee, Euntai Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 5374-5384


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:

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Lee_2022_CVPR, author = {Lee, Seongwon and Seong, Hongje and Lee, Suhyeon and Kim, Euntai}, title = {Correlation Verification for Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5374-5384} }