Hypergraph Propagation and Community Selection for Objects Retrieval
Spatial verification is a crucial technique for particular object retrieval. It utilizes spatial information for the accurate detection of true positive images. However, existing query expansion and diffusion methods cannot efficiently propagate the spatial information in an ordinary graph with scalar edge weights, resulting in low recall or precision. To tackle these problems, we propose a novel hypergraph-based framework that efficiently propagates spatial information in query time and retrieves an object in the database accurately. Additionally, we propose using the image graph's structure information through community selection technique, to measure the accuracy of the initial search result and to provide correct starting points for hypergraph propagation without heavy spatial verification computations. Experiment results on ROxford and RParis show that our method significantly outperforms the existing query expansion and diffusion methods.
PDF Abstract NeurIPS 2021 PDF NeurIPS 2021 AbstractDatasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Image Retrieval | ROxford (Hard) | Hypergraph propagation+community selection | mAP | 73 | # 2 | |
Image Retrieval | ROxford (Medium) | Hypergraph propagation+Community selection | mAP | 88.4 | # 1 | |
Image Retrieval | RParis (Hard) | Hypergraph propagation | mAP | 83.3 | # 2 | |
Image Retrieval | RParis (Medium) | Hypergraph propagation | mAP | 92.6 | # 1 |