Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval

2026-08-30

AI Summary

本文提出ColSNAP方法，通过空间池化和同时训练不同压缩层级来解决视觉文档检索中的高存储成本问题，支持灵活的精度-存储权衡。

Abstract

Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. However, this approach incurs high storage costs. Existing compression methods typically fix a single compression level at indexing time, limiting flexibility. We present ColSNAP (Spatial Nested Average Pooling)1, a training method that generates a nested hierarchy of compression levels directly from a backbone's patch grid. By spatially pooling patch embeddings into pro- gressively coarser tiers and training all tiers simultaneously, a single model learns to support retrieval at multiple compression levels without architectural changes. Crucially, a single encoding pass yields every tier, enabling the accuracy-storage trade-off to be configured at indexing time to match avail- able storage budgets, rather than being fixed during training. We demonstrate that models trained using ColSNAP maintain near full-resolution retrieval performance under substantial compression and that ColSNAP transfers effectively across multiple late-interaction backbones, and achieves most of its improvements via a lightweight adaptation stage applied to a pre-trained retriever.

Problem

• multi-modal late-interaction retrievers
• visually rich documents
• high storage costs
• compression levels
• indexing time

Innovation

• Spatial Nested Average Pooling
• multi-granularity retrieval
• compression levels
• storage efficiency
• flexible indexing