DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912612903550976 |
|---|---|
| author | Yan, Yibo Xu, Guangwei Zou, Xin Liu, Shuliang Kwok, James Hu, Xuming |
| author_facet | Yan, Yibo Xu, Guangwei Zou, Xin Liu, Shuliang Kwok, James Hu, Xuming |
| contents | Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applications. Recent state-of-the-art methods leverage Large Vision-Language Models (LVLMs) in a multi-vector paradigm, representing each document as patch-level embeddings to capture fine-grained details. While highly effective, this approach introduces a critical challenge: prohibitive storage overhead, as storing hundreds of vectors per page makes large-scale deployment costly and impractical. To address this, we introduce DocPruner, the first framework to employ adaptive patch-level embedding pruning for VDR to effectively reduce the storage overhead. DocPruner leverages the intra-document patch attention distribution to dynamically identify and discard redundant embeddings for each document. This adaptive mechanism enables a significant 50-60% reduction in storage for leading multi-vector VDR models with negligible degradation in document retrieval performance. Extensive experiments across more than ten representative datasets validate that DocPruner offers a robust, flexible, and effective solution for building storage-efficient, large-scale VDR systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23883 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning Yan, Yibo Xu, Guangwei Zou, Xin Liu, Shuliang Kwok, James Hu, Xuming Computation and Language Information Retrieval Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applications. Recent state-of-the-art methods leverage Large Vision-Language Models (LVLMs) in a multi-vector paradigm, representing each document as patch-level embeddings to capture fine-grained details. While highly effective, this approach introduces a critical challenge: prohibitive storage overhead, as storing hundreds of vectors per page makes large-scale deployment costly and impractical. To address this, we introduce DocPruner, the first framework to employ adaptive patch-level embedding pruning for VDR to effectively reduce the storage overhead. DocPruner leverages the intra-document patch attention distribution to dynamically identify and discard redundant embeddings for each document. This adaptive mechanism enables a significant 50-60% reduction in storage for leading multi-vector VDR models with negligible degradation in document retrieval performance. Extensive experiments across more than ten representative datasets validate that DocPruner offers a robust, flexible, and effective solution for building storage-efficient, large-scale VDR systems. |
| title | DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2509.23883 |