将图像分块匹配，实现精准且可解释的实例级检索
Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
- 将图像划分为结构化小块，通过局部特征与全局查询比对实现匹配
- 在多个数据集上超越传统全局方法，定位准确率显著提升
- 适合需要高精度定位的视觉检索场景，如工业质检或医疗影像
实例级图像检索旨在找到包含与查询图像相同物体的图片，即使存在尺度、位置或外观变化。为此，我们提出 Patchify——一种简单而有效的分块检索框架，无需微调即可实现高性能、可扩展性和可解释性。Patchify 将每张数据库图像划分为少量结构化图像块，并通过比较这些局部特征与全局查询描述符进行检索，实现准确且空间对齐的匹配。为评估检索的准确性与空间正确性，我们引入 LocScore，一种关注定位的度量指标，用于量化检索区域是否与目标物体对齐，可作为理解并改进检索行为的重要诊断工具。我们在多个基准测试、主干网络和区域选择策略下进行了广泛实验，结果表明 Patchify 在性能上优于全局方法，并能有效补充当前最先进的重排序流程。此外，我们采用产品量化（Product Quantization）实现高效的大规模检索，并强调在压缩过程中使用有信息量的特征至关重要，能显著提升性能。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。