SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Thong, Lei, Yibin, Ju, Jia-Huei, Yates, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909797356404736
author Nguyen, Thong
Lei, Yibin
Ju, Jia-Huei
Yates, Andrew
author_facet Nguyen, Thong
Lei, Yibin
Ju, Jia-Huei
Yates, Andrew
contents Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first produces a detailed textual description of each document image, which is then embedded by a standard text encoder. On the ViDoRe-v2 benchmark, the method reaches 63.4% nDCG@5, surpassing the strongest specialised multi-vector visual document encoder. It also scales better to large collections and offers broader multilingual coverage. Analysis shows that modern vision-language models capture complex textual and visual cues with sufficient granularity to act as a reusable semantic proxy. By offloading modality alignment to pretrained vision-language models, our approach removes the need for computationally intensive text-image contrastive training and establishes a strong zero-shot baseline for future VDR systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15432
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models
Nguyen, Thong
Lei, Yibin
Ju, Jia-Huei
Yates, Andrew
Information Retrieval
Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first produces a detailed textual description of each document image, which is then embedded by a standard text encoder. On the ViDoRe-v2 benchmark, the method reaches 63.4% nDCG@5, surpassing the strongest specialised multi-vector visual document encoder. It also scales better to large collections and offers broader multilingual coverage. Analysis shows that modern vision-language models capture complex textual and visual cues with sufficient granularity to act as a reusable semantic proxy. By offloading modality alignment to pretrained vision-language models, our approach removes the need for computationally intensive text-image contrastive training and establishes a strong zero-shot baseline for future VDR systems.
title SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models
topic Information Retrieval
url https://arxiv.org/abs/2509.15432