QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding
- URL: http://arxiv.org/abs/2504.02971v2
- Date: Mon, 07 Apr 2025 17:58:44 GMT
- Title: QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding
- Authors: Binh M. Le, Shaoyuan Xu, Jinmiao Fu, Zhishen Huang, Moyan Li, Yanhui Guo, Hongdong Li, Sameera Ramasinghe, Bryan Wang,
- Abstract summary: Fine-tuning a pre-trained Vision-Language Model with new datasets often falls short in optimizing the vision encoder.<n>We introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder.
- Score: 53.69841526266547
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify query-specific regions in text-rich document images. Existing methods that directly inject queries into model layers by modifying the network architecture often struggle to adapt to new datasets with limited annotations. To address this, we introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder, leading to notable performance gains, particularly in data-scarce fine-tuning scenarios. Specifically, our approach introduces a dual-module framework: a query-aware module that generates a unique query vector to precisely guide the model's focus, as well as a query-agnostic module that captures the positional relationships among tokens, ensuring robust spatial understanding. Notably, both modules operate independently of the vision attention blocks, facilitating targeted learning of query embeddings and enhancing visual semantic identification. Experiments with OCR-free VLMs across multiple datasets demonstrate significant performance improvements using our method, especially in handling text-rich documents in data-scarce environments.
Related papers
- Improving Large Vision-Language Models' Understanding for Field Data [62.917026891829025]
We introduce FieldLVLM, a framework designed to improve large vision-language models' understanding of field data.<n>FieldLVLM consists of two main components: a field-aware language generation strategy and a data-compressed multimodal model tuning.<n> Experimental results on newly proposed benchmark datasets demonstrate that FieldLVLM significantly outperforms existing methods in tasks involving scientific field data.
arXiv Detail & Related papers (2025-07-24T11:28:53Z) - An analysis of vision-language models for fabric retrieval [4.311804611758908]
Cross-modal retrieval is essential for applications like information retrieval and recommendation systems.<n>This paper investigates the use of Vision Language Models for zero-shot text-to-image retrieval on fabric samples.
arXiv Detail & Related papers (2025-07-07T08:00:18Z) - Doc-CoB: Enhancing Multi-Modal Document Understanding with Visual Chain-of-Boxes Reasoning [12.17399365931]
Existing one-pass MLLMs process entire document images without considering query relevance.<n>Inspired by the human coarse-to-fine reading pattern, we introduce Doc-CoB, a simple-yet-effective mechanism that integrates human-style visual reasoning into MLLM.<n>Our method allows the model to autonomously select the set of regions most relevant to the query, and then focus attention on them for further understanding.
arXiv Detail & Related papers (2025-05-24T08:53:05Z) - SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation [5.458935851230595]
We present SCAN, a novel approach enhancing both textual and visual Retrieval-Augmented Generation (RAG) systems.<n>SCAN uses a coarse-grained semantic approach that divides documents into coherent regions covering continuous components.<n>Our experimental results across English and Japanese datasets demonstrate that applying SCAN improves end-to-end textual RAG performance by up to 9.0% and visual RAG performance by up to 6.4%.
arXiv Detail & Related papers (2025-05-20T14:03:24Z) - A Multi-Granularity Retrieval Framework for Visually-Rich Documents [4.804551482123172]
We propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR.<n>Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering.<n>Our framework demonstrates robust performance without the need for task-specific fine-tuning.
arXiv Detail & Related papers (2025-05-01T02:40:30Z) - Unlocking the Capabilities of Vision-Language Models for Generalizable and Explainable Deepfake Detection [18.125287697902813]
Current vision-language models (VLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake detection.<n>We present a novel paradigm that unlocksVLMs' potential capabilities through three components.
arXiv Detail & Related papers (2025-03-19T03:20:03Z) - OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models [58.45517851437422]
Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understanding.<n>Existing solutions often rely on task-specific architectures and objectives for individual tasks.<n>In this paper, we introduce Omni V2, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis.
arXiv Detail & Related papers (2025-02-22T09:32:01Z) - Towards Text-Image Interleaved Retrieval [49.96332254241075]
We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
arXiv Detail & Related papers (2025-02-18T12:00:47Z) - VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation [100.06122876025063]
This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings.<n>We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG.
arXiv Detail & Related papers (2024-12-14T06:24:55Z) - Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data.
We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation.
Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
arXiv Detail & Related papers (2024-10-31T06:55:24Z) - HRVDA: High-Resolution Visual Document Assistant [32.51417315241559]
We propose a High-Resolution Visual Document Assistant (HRVDA) to bridge the gap between MLLMs and visual document understanding.
HRVDA employs a content filtering mechanism and an instruction filtering module to filter out the content-agnostic visual tokens and instruction-agnostic visual tokens.
Our model achieves state-of-the-art performance across multiple document understanding datasets.
arXiv Detail & Related papers (2024-04-10T11:10:50Z) - RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation.
Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal.
We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
arXiv Detail & Related papers (2023-07-03T13:21:58Z) - Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction [13.454953507205278]
Multi-Modal Relation Extraction aims at identifying the relation between two entities in texts that contain visual clues.
We propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects.
Our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.
arXiv Detail & Related papers (2023-06-19T15:31:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.