Instance-level Image Retrieval Using Reranking Transformers

Abstract

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

Stats

• citations89
• S2 citations—
• github stars147
• HF likes0
• heat score19.00
• arxiv keytan2021instance

Related papers

• Training Vision Transformers For Image Retrieval (2021)0.00
• \(r^{2}\)former: Unified \(r\)etrieval And \(r\)eranking Transformer For Place Recognition (2023)18.31
• Boosting Vision Transformers For Image Retrieval (2022)15.28
• Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00
• Faster R-CNN Features For Instance Search (2016)14.62
• STIR: Siamese Transformer For Image Retrieval Postprocessing (2023)11.23
• Referring Expression Instance Retrieval And A Strong End-to-end Baseline (2025)0.00
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00