MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval

• URL: http://arxiv.org/abs/2411.08334v2
• Date: Mon, 17 Feb 2025 01:49:01 GMT
• Title: MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval
• Authors: Yeong-Joon Ju, Ho-Joong Kim, Seong-Whan Lee,
• Abstract summary: We introduce MIRe, a retrieval framework that achieves modality interaction without fusing textual features during the alignment. Our method allows the textual query to attend to visual embeddings while not feeding text-driven signals back into the visual representations. Our experiments demonstrate that our pre-training strategy significantly enhances the understanding of multimodal queries.
• Score: 26.585985828583304
• License:
• Abstract: Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the alignment to understand multimodal queries. However, existing methods often overlook crucial visual information due to a text-dominant issue, which overly depends on text-driven signals. In this paper, we introduce MIRe, a retrieval framework that achieves modality interaction without fusing textual features during the alignment. Our method allows the textual query to attend to visual embeddings while not feeding text-driven signals back into the visual representations. Additionally, we construct a pre-training dataset for multimodal query retrieval by transforming concise question-answer pairs into extended passages. Our experiments demonstrate that our pre-training strategy significantly enhances the understanding of multimodal queries, resulting in strong performance across four multimodal retrieval benchmarks under zero-shot settings. Our code is publicly available: https://github.com/yeongjoonJu/MIRe.

Related papers

• 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. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. 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)
• Multi-Turn Multi-Modal Question Clarification for Enhanced Conversational Understanding [11.004677535859342]
  We introduce the Multi-turn Multi-modal Clarifying Questions (MMCQ) task. MMCQ combines text and visual modalities to refine user queries in a multi-turn conversation. We show that multi-turn multi-modal clarification outperforms uni-modal and single-turn approaches, improving MRR by 12.88%.
  arXiv  Detail & Related papers  (2025-02-17T04:58:14Z)
• MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs [78.5013630951288]
  This paper introduces techniques for advancing information retrieval with multimodal large language models (MLLMs) We first study fine-tuning an MLLM as a bi-encoder retriever on 10 datasets with 16 retrieval tasks. We propose modality-aware hard negative mining to mitigate the modality bias exhibited by MLLM retrievers.
  arXiv  Detail & Related papers  (2024-11-04T20:06:34Z)
• Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification [74.45521856327001]
  How to classify long documents with hierarchical structure texts and embedding images is a new problem. We propose a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification. Our approach uses a multi-modal transformer and a dynamic multi-scale multi-modal transformer to model the complex relationships between image features, and the section and sentence features.
  arXiv  Detail & Related papers  (2024-07-14T07:12:25Z)
• VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval [10.603148564713518]
  We present a new embedding model VISTA for universal multi-modal retrieval. We introduce a flexible architecture which extends a powerful text encoder with the image understanding capability. Secondly, we develop two data generation strategies, which bring high-quality composed image-text to facilitate the training of the embedding model.
  arXiv  Detail & Related papers  (2024-06-06T17:37:47Z)
• Multi-modal Stance Detection: New Datasets and Model [56.97470987479277]
  We study multi-modal stance detection for tweets consisting of texts and images. We propose a simple yet effective Targeted Multi-modal Prompt Tuning framework (TMPT) TMPT achieves state-of-the-art performance in multi-modal stance detection.
  arXiv  Detail & Related papers  (2024-02-22T05:24:19Z)
• 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)
• CISum: Learning Cross-modality Interaction to Enhance Multimodal Semantic Coverage for Multimodal Summarization [2.461695698601437]
  This paper proposes a multi-task cross-modality learning framework (CISum) to improve multimodal semantic coverage. To obtain the visual semantics, we translate images into visual descriptions based on the correlation with text content. Then, the visual description and text content are fused to generate the textual summary to capture the semantics of the multimodal content.
  arXiv  Detail & Related papers  (2023-02-20T11:57:23Z)
• TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents [51.744527199305445]
  This paper proposes a unified end-to-end information extraction framework from visually rich documents. Text reading and information extraction can reinforce each other via a well-designed multi-modal context block. The framework can be trained in an end-to-end trainable manner, achieving global optimization.
  arXiv  Detail & Related papers  (2022-07-14T08:52:07Z)

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.