Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kang, Lei, Tito, Rubèn, Valveny, Ernest, Karatzas, Dimosthenis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914777000837120
author Kang, Lei
Tito, Rubèn
Valveny, Ernest
Karatzas, Dimosthenis
author_facet Kang, Lei
Tito, Rubèn
Valveny, Ernest
Karatzas, Dimosthenis
contents Documents are 2-dimensional carriers of written communication, and as such their interpretation requires a multi-modal approach where textual and visual information are efficiently combined. Document Visual Question Answering (Document VQA), due to this multi-modal nature, has garnered significant interest from both the document understanding and natural language processing communities. The state-of-the-art single-page Document VQA methods show impressive performance, yet in multi-page scenarios, these methods struggle. They have to concatenate all pages into one large page for processing, demanding substantial GPU resources, even for evaluation. In this work, we propose a novel method and efficient training strategy for multi-page Document VQA tasks. In particular, we employ a visual-only document representation, leveraging the encoder from a document understanding model, Pix2Struct. Our approach utilizes a self-attention scoring mechanism to generate relevance scores for each document page, enabling the retrieval of pertinent pages. This adaptation allows us to extend single-page Document VQA models to multi-page scenarios without constraints on the number of pages during evaluation, all with minimal demand for GPU resources. Our extensive experiments demonstrate not only achieving state-of-the-art performance without the need for Optical Character Recognition (OCR), but also sustained performance in scenarios extending to documents of nearly 800 pages compared to a maximum of 20 pages in the MP-DocVQA dataset. Our code is publicly available at \url{https://github.com/leitro/SelfAttnScoring-MPDocVQA}.
format Preprint
id arxiv_https___arxiv_org_abs_2404_19024
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
Kang, Lei
Tito, Rubèn
Valveny, Ernest
Karatzas, Dimosthenis
Computer Vision and Pattern Recognition
Documents are 2-dimensional carriers of written communication, and as such their interpretation requires a multi-modal approach where textual and visual information are efficiently combined. Document Visual Question Answering (Document VQA), due to this multi-modal nature, has garnered significant interest from both the document understanding and natural language processing communities. The state-of-the-art single-page Document VQA methods show impressive performance, yet in multi-page scenarios, these methods struggle. They have to concatenate all pages into one large page for processing, demanding substantial GPU resources, even for evaluation. In this work, we propose a novel method and efficient training strategy for multi-page Document VQA tasks. In particular, we employ a visual-only document representation, leveraging the encoder from a document understanding model, Pix2Struct. Our approach utilizes a self-attention scoring mechanism to generate relevance scores for each document page, enabling the retrieval of pertinent pages. This adaptation allows us to extend single-page Document VQA models to multi-page scenarios without constraints on the number of pages during evaluation, all with minimal demand for GPU resources. Our extensive experiments demonstrate not only achieving state-of-the-art performance without the need for Optical Character Recognition (OCR), but also sustained performance in scenarios extending to documents of nearly 800 pages compared to a maximum of 20 pages in the MP-DocVQA dataset. Our code is publicly available at \url{https://github.com/leitro/SelfAttnScoring-MPDocVQA}.
title Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.19024