Instance-level Image Retrieval using Reranking Transformers
Instance-level Image Retrieval using Reranking Transformers
复制标题
DOI：
10.1109/iccv48922.2021.01189
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Fuwen Tan;Jiangbo Yuan;Vicente Ordonez
中科院分区：
文献类型：
--
作者：
Fuwen Tan;Jiangbo Yuan;Vicente Ordonez
实例级图像检索是在大型数据库中搜索与查询图像中的对象匹配的图像的任务。为了解决这一任务，系统通常依赖于使用全局图像描述符的检索步骤，以及通过利用诸如基于局部特征的几何验证等操作来执行特定于域的细化或重新排序的后续步骤。在这项工作中，我们建议重新排序变换(RRT)作为一个通用的模型，结合局部和全局特征，以有监督的方式对匹配图像进行重新排序，从而取代相对昂贵的几何验证过程。RRT是轻量级的，可以很容易地并行化，从而可以在单个前向传递中执行对一组顶级匹配结果的重新排序。我们在Revisted Oxford和Paris数据集以及Google Landmarksv2数据集上进行了广泛的实验，表明RRT在使用更少的局部描述符的情况下，性能优于以前的重新排序方法。此外，我们证明，与现有方法不同的是，RRT可以与特征抽取器一起优化，这可以导致针对下游任务的特征表示，并进一步提高精度。代码和经过培训的模型可在https://github.com/uvavision/RerankingTransformer.上公开获取
Instance-level image retrieval is the task of searching in a large database for images that match an object in a query image. To address this task, systems usually rely on a retrieval step that uses global image descriptors, and a subsequent step that performs domain-specific refinements or reranking by leveraging operations such as geometric verification based on local features. In this work, we propose Reranking Transformers (RRTs) as a general model to incorporate both local and global features to rerank the matching images in a supervised fashion and thus replace the relatively expensive process of geometric verification. RRTs are lightweight and can be easily parallelized so that reranking a set of top matching results can be performed in a single forward-pass. We perform extensive experiments on the Revisited Oxford and Paris datasets, and the Google Landmarks v2 dataset, showing that RRTs outperform previous reranking approaches while using much fewer local descriptors. Moreover, we demonstrate that, unlike existing approaches, RRTs can be optimized jointly with the feature extractor, which can lead to feature representations tailored to downstream tasks and further accuracy improvements. The code and trained models are publicly available at https://github.com/uvavision/RerankingTransformer.