Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Choi, Wonseok, Lim, Sohwi, Hyeon-Woo, Nam, Ye-Bin, Moon, Jeong, Dong-Ju, Hwang, Jinyoung, Oh, Tae-Hyun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908711223558144
author Choi, Wonseok
Lim, Sohwi
Hyeon-Woo, Nam
Ye-Bin, Moon
Jeong, Dong-Ju
Hwang, Jinyoung
Oh, Tae-Hyun
author_facet Choi, Wonseok
Lim, Sohwi
Hyeon-Woo, Nam
Ye-Bin, Moon
Jeong, Dong-Ju
Hwang, Jinyoung
Oh, Tae-Hyun
contents Instance-level image retrieval aims to find images containing the same object as a given query, despite variations in size, position, or appearance. To address this challenging task, we propose Patchify, a simple yet effective patch-wise retrieval framework that offers high performance, scalability, and interpretability without requiring fine-tuning. Patchify divides each database image into a small number of structured patches and performs retrieval by comparing these local features with a global query descriptor, enabling accurate and spatially grounded matching. To assess not just retrieval accuracy but also spatial correctness, we introduce LocScore, a localization-aware metric that quantifies whether the retrieved region aligns with the target object. This makes LocScore a valuable diagnostic tool for understanding and improving retrieval behavior. We conduct extensive experiments across multiple benchmarks, backbones, and region selection strategies, showing that Patchify outperforms global methods and complements state-of-the-art reranking pipelines. Furthermore, we apply Product Quantization for efficient large-scale retrieval and highlight the importance of using informative features during compression, which significantly boosts performance. Project website: https://wons20k.github.io/PatchwiseRetrieval/
format Preprint
id arxiv_https___arxiv_org_abs_2512_12610
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
Choi, Wonseok
Lim, Sohwi
Hyeon-Woo, Nam
Ye-Bin, Moon
Jeong, Dong-Ju
Hwang, Jinyoung
Oh, Tae-Hyun
Computer Vision and Pattern Recognition
Information Retrieval
Instance-level image retrieval aims to find images containing the same object as a given query, despite variations in size, position, or appearance. To address this challenging task, we propose Patchify, a simple yet effective patch-wise retrieval framework that offers high performance, scalability, and interpretability without requiring fine-tuning. Patchify divides each database image into a small number of structured patches and performs retrieval by comparing these local features with a global query descriptor, enabling accurate and spatially grounded matching. To assess not just retrieval accuracy but also spatial correctness, we introduce LocScore, a localization-aware metric that quantifies whether the retrieved region aligns with the target object. This makes LocScore a valuable diagnostic tool for understanding and improving retrieval behavior. We conduct extensive experiments across multiple benchmarks, backbones, and region selection strategies, showing that Patchify outperforms global methods and complements state-of-the-art reranking pipelines. Furthermore, we apply Product Quantization for efficient large-scale retrieval and highlight the importance of using informative features during compression, which significantly boosts performance. Project website: https://wons20k.github.io/PatchwiseRetrieval/
title Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
topic Computer Vision and Pattern Recognition
Information Retrieval
url https://arxiv.org/abs/2512.12610