用代表性页面合成文档图像，实现高效文档级视觉检索
DocPC: Document-Level Visual Retrieval via Representative Page Composition
- 选取关键页面合成单张网格图，实现文档级统一索引
- 在DocViRe上达NDCG@5 44.09，存储减少10.1倍
- 适合需要跨页检索的文档处理场景
视觉文档检索通过使用视觉语言模型编码页面截图，跳过了OCR流程。然而，现有方法仍以页面为中心，与真实场景中需完整文档检索的需求不匹配。简单的页面后聚合方式存在线性索引成本高、多页相关性导致检索性能下降的问题。本文提出DocPC框架，基于代表性页面组合：选择代表性页面并将其组合成一张网格图像用于文档级索引，使索引图像、向量和存储量减少10.1倍，端到端索引时间减少约7.7倍。为应对文档级别常见的多正样本监督，结合多正例对比学习与稀疏调度的列表优化。同时引入DocViRe基准数据集，包含多正例相关性标注。DocPC-ColQwen在DocViRe上达到NDCG@5 44.09，优于最强页面级基线（38.91），同时存储减少10.1倍。代码与数据已在匿名开源平台发布。
原文摘要 · Abstract (English)
Visual document retrieval has advanced by encoding page screenshots with vision-language models, bypassing OCR pipelines. However, existing methods remain page-centric, misaligned with real-world scenarios requiring complete document retrieval. A naive page-then-document aggregation suffers from linear indexing cost and degraded retrieval when relevance spans multiple pages. We propose DocPC, a document-level visual retrieval framework based on Representative Page Composition: selecting representative pages and composing them into a single grid image for document-level indexing, reducing indexed images, vectors, and storage by 10.1x and end-to-end indexing time by roughly 7.7x. To handle multi-positive supervision prevalent at the document level, we combine multi-positive contrastive learning with sparsely scheduled listwise optimization. We also introduce DocViRe, a benchmark with multi-positive relevance annotations. DocPC-ColQwen achieves NDCG@5 of 44.09 on DocViRe, outperforming the strongest page-level baseline at 38.91 while reducing storage by 10.1x. Code is available at https://anonymous.4open.science/r/DocPC-Document-Level-Visual-Retrieval-via-Representative-Page-Composition-1D52. Data is available at https://huggingface.co/datasets/anonymous-7219/docpc.
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。