UniRVQA: A Unified Framework for Retrieval-Augmented Vision Question Answering via Self-Reflective Joint Training

• URL: http://arxiv.org/abs/2504.04065v1
• Date: Sat, 05 Apr 2025 05:42:12 GMT
• Title: UniRVQA: A Unified Framework for Retrieval-Augmented Vision Question Answering via Self-Reflective Joint Training
• Authors: Jiaqi Deng, Kaize Shi, Zonghan Wu, Huan Huo, Dingxian Wang, Guandong Xu,
• Abstract summary: We propose a Unified Retrieval-Augmented VQA framework (UniRVQA) for knowledge-intensive visual questions.<n>UniRVQA adapts general multimodal pre-trained models for fine-grained knowledge-intensive tasks within a unified framework.<n>Our approach achieves competitive performance against state-of-the-art models, delivering a significant 4.7% improvement in answering accuracy, and brings an average 7.5% boost in base MLLMs' VQA performance.
• Score: 16.14877145354785
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions requiring external knowledge, such as web-sourced encyclopedia articles. Existing methods often use sequential and separate frameworks for the retriever and the generator with limited parametric knowledge sharing. However, since both retrieval and generation tasks require accurate understanding of contextual and external information, such separation can potentially lead to suboptimal system performance. Another key challenge is the integration of multimodal information. General-purpose multimodal pre-trained models, while adept at multimodal representation learning, struggle with fine-grained retrieval required for knowledge-intensive visual questions. Recent specialized pre-trained models mitigate the issue, but are computationally expensive. To bridge the gap, we propose a Unified Retrieval-Augmented VQA framework (UniRVQA). UniRVQA adapts general multimodal pre-trained models for fine-grained knowledge-intensive tasks within a unified framework, enabling cross-task parametric knowledge sharing and the extension of existing multimodal representation learning capability. We further introduce a reflective-answering mechanism that allows the model to explicitly evaluate and refine its knowledge boundary. Additionally, we integrate late interaction into the retrieval-augmented generation joint training process to enhance fine-grained understanding of queries and documents. Our approach achieves competitive performance against state-of-the-art models, delivering a significant 4.7% improvement in answering accuracy, and brings an average 7.5% boost in base MLLMs' VQA performance.

Related papers

• Open-Ended and Knowledge-Intensive Video Question Answering [20.256081440725353]
  We investigate knowledge-intensive video question answering (KI-VideoQA) through the lens of multi-modal retrieval-augmented generation.<n>Our analysis examines various retrieval augmentation approaches using cutting-edge retrieval and vision language models.<n>We achieve a substantial 17.5% improvement in accuracy on multiple choice questions in the KnowIT VQA dataset.
  arXiv  Detail & Related papers  (2025-02-17T12:40:35Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• Multimodal Reranking for Knowledge-Intensive Visual Question Answering [77.24401833951096]
  We introduce a multi-modal reranker to improve the ranking quality of knowledge candidates for answer generation. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements.
  arXiv  Detail & Related papers  (2024-07-17T02:58:52Z)
• RAVEN: Multitask Retrieval Augmented Vision-Language Learning [5.1583788731239455]
  The scaling of large language models to encode all the world's knowledge is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to vision-language models (VLMs) is under explored. This paper introduces RAVEN, a retrieval augmented VLM framework that enhances base VLMs through efficient, task specific fine-tuning.
  arXiv  Detail & Related papers  (2024-06-27T13:08:35Z)
• Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
  We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning) The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs. It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:23:49Z)
• Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering [47.668572102657684]
  This work introduces a novel, explainable multi-agent collaboration framework by leveraging the expansive knowledge of Large Language Models (LLMs) to enhance the capabilities of Vision Language Models (VLMs)
  arXiv  Detail & Related papers  (2023-11-29T03:10:42Z)
• Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering [16.52970318866536]
  This paper studies a category of visual question answering tasks, in which accessing external knowledge is necessary for answering the questions. A major step in developing OK-VQA systems is to retrieve relevant documents for the given multi-modal query. We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks.
  arXiv  Detail & Related papers  (2023-06-28T18:06:40Z)
• End-to-end Knowledge Retrieval with Multi-modal Queries [50.01264794081951]
  ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion. We demonstrate superior performance in retrieval on two datasets under zero-shot settings.
  arXiv  Detail & Related papers  (2023-06-01T08:04:12Z)
• Retrieval Augmented Visual Question Answering with Outside Knowledge [14.371342370460685]
  Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to retrieve documents from external knowledge bases, such as Wikipedia, but with DPR trained separately from answer generation. We propose a joint training scheme which includes differentiable DPR integrated with answer generation so that the system can be trained in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-10-07T20:35:58Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• KAT: A Knowledge Augmented Transformer for Vision-and-Language [56.716531169609915]
  We propose a novel model - Knowledge Augmented Transformer (KAT) - which achieves a strong state-of-the-art result on the open-domain multimodal task of OK-VQA. Our approach integrates implicit and explicit knowledge in an end to end encoder-decoder architecture, while still jointly reasoning over both knowledge sources during answer generation. An additional benefit of explicit knowledge integration is seen in improved interpretability of model predictions in our analysis.
  arXiv  Detail & Related papers  (2021-12-16T04:37:10Z)

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.