Detect-to-retrieve: Efficient Regional Aggregation For Image Search

Abstract

Retrieving object instances among cluttered scenes efficiently requires compact yet comprehensive regional image representations. Intuitively, object semantics can help build the index that focuses on the most relevant regions. However, due to the lack of bounding-box datasets for objects of interest among retrieval benchmarks, most recent work on regional representations has focused on either uniform or class-agnostic region selection. In this paper, we first fill the void by providing a new dataset of landmark bounding boxes, based on the Google Landmarks dataset, that includes \(86k\) images with manually curated boxes from \(15k\) unique landmarks. Then, we demonstrate how a trained landmark detector, using our new dataset, can be leveraged to index image regions and improve retrieval accuracy while being much more efficient than existing regional methods. In addition, we introduce a novel regional aggregated selective match kernel (R-ASMK) to effectively combine information from d

Stats

• citations97
• S2 citations—
• github stars77667
• HF likes0
• heat score24.71
• arxiv keyteichmann2018detect

Related papers

• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Adversarial Soft-detection-based Aggregation Network For Image Retrieval (2018)0.00
• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Investigating The Role Of Image Retrieval For Visual Localization -- An Exhaustive Benchmark (2022)16.58
• Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching (2025)0.00
• Resedis: A Dataset For Referring-based Object Search Across Large-scale Image Collections (2025)0.00
• Semi-supervised Exploration In Image Retrieval (2019)0.00
• Unsupervised Object Discovery For Instance Recognition (2017)6.77