Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching

Abstract

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 outperf

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychoi2025patch

Related papers

• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47
• Spatially-grounded Document Retrieval Via Patch-to-region Relevance Propagation (2025)3.86
• Detect-to-retrieve: Efficient Regional Aggregation For Image Search (2018)24.71
• AMES: Asymmetric And Memory-efficient Similarity Estimation For Instance-level Retrieval (2024)9.70
• Patch2cad: Patchwise Embedding Learning For In-the-wild Shape Retrieval From A Single Image (2021)10.85
• To Match Or Not To Match: Revisiting Image Matching For Reliable Visual Place Recognition (2025)5.46
• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Connecting Images Through Time And Sources: Introducing Low-data, Heterogeneous Instance Retrieval (2021)0.00