Correlation Verification for Image Retrieval
Seongwon Lee, Hongje Seong, Suhyeon Lee, Euntai Kim

TL;DR
This paper introduces CVNet, a novel deep learning-based re-ranking network for image retrieval that effectively models geometric correlations and improves accuracy significantly over existing methods.
Contribution
The paper presents CVNet, a deep 4D convolutional network with cross-scale feature correlation and curriculum learning, achieving state-of-the-art results in image retrieval re-ranking.
Findings
+12.6% in mAP on ROxford-Hard+1M benchmark
State-of-the-art performance on multiple retrieval benchmarks
Effective cross-scale matching with reduced inference cost
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Multimodal Machine Learning Applications
