Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation

• URL: http://arxiv.org/abs/2505.21956v2
• Date: Thu, 29 May 2025 03:27:40 GMT
• Title: Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation
• Authors: Mengdan Zhu, Senhao Cheng, Guangji Bai, Yifei Zhang, Liang Zhao,
• Abstract summary: We propose Cross-modal RAG, a novel framework that decomposes both queries and images into sub-dimensional components.<n>Our method introduces a hybrid retrieval strategy - combining a sub-dimensional sparse retriever with a dense retriever.<n>Experiments on MS-COCO, Flickr30K, WikiArt, CUB, and ImageNet-LT demonstrate that Cross-modal RAG significantly outperforms existing baselines in both retrieval and generation quality.
• Score: 12.631059980161435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image generation increasingly demands access to domain-specific, fine-grained, and rapidly evolving knowledge that pretrained models cannot fully capture. Existing Retrieval-Augmented Generation (RAG) methods attempt to address this by retrieving globally relevant images, but they fail when no single image contains all desired elements from a complex user query. We propose Cross-modal RAG, a novel framework that decomposes both queries and images into sub-dimensional components, enabling subquery-aware retrieval and generation. Our method introduces a hybrid retrieval strategy - combining a sub-dimensional sparse retriever with a dense retriever - to identify a Pareto-optimal set of images, each contributing complementary aspects of the query. During generation, a multimodal large language model is guided to selectively condition on relevant visual features aligned to specific subqueries, ensuring subquery-aware image synthesis. Extensive experiments on MS-COCO, Flickr30K, WikiArt, CUB, and ImageNet-LT demonstrate that Cross-modal RAG significantly outperforms existing baselines in both retrieval and generation quality, while maintaining high efficiency.

Related papers

• Enhancing Multi-Image Question Answering via Submodular Subset Selection [16.66633426354087]
  Large multimodal models (LMMs) have achieved high performance in vision-language tasks involving single image but struggle when presented with a collection of multiple images.<n>We propose an enhancement for retriever framework introduced in MIRAGE model using submodular subset selection techniques.
  arXiv  Detail & Related papers  (2025-05-15T17:41:52Z)
• 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)
• 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)
• ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation [26.4086456393314]
  Long-form text generation requires coherent, comprehensive responses that address complex queries with both breadth and depth. Existing iterative retrieval-augmented generation approaches often struggle to delve deeply into each facet of complex queries. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach.
  arXiv  Detail & Related papers  (2024-10-20T21:17:05Z)
• TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models [96.72318842152148]
  We propose a unified framework for text-to-image generation and retrieval with one single Large Multimodal Model (LMM)<n> Specifically, we first explore the intrinsic discriminative abilities of LMMs and introduce an efficient generative retrieval method for text-to-image retrieval in a training-free manner.<n>We then propose an autonomous decision mechanism to choose the best-matched one between generated and retrieved images as the response to the text prompt.
  arXiv  Detail & Related papers  (2024-06-09T15:00:28Z)
• A Multimodal Approach for Cross-Domain Image Retrieval [5.5547914920738]
  Cross-Domain Image Retrieval (CDIR) is a challenging task in computer vision. This paper introduces a novel unsupervised approach to CDIR that incorporates textual context by leveraging pre-trained vision-language models. Our method, dubbed as Caption-Matching (CM), uses generated image captions as a domain-agnostic intermediate representation.
  arXiv  Detail & Related papers  (2024-03-22T12:08:16Z)
• JourneyDB: A Benchmark for Generative Image Understanding [89.02046606392382]
  We introduce a comprehensive dataset, referred to as JourneyDB, that caters to the domain of generative images. Our meticulously curated dataset comprises 4 million distinct and high-quality generated images. On our dataset, we have devised four benchmarks to assess the performance of generated image comprehension.
  arXiv  Detail & Related papers  (2023-07-03T02:39:08Z)
• Re-Imagen: Retrieval-Augmented Text-to-Image Generator [58.60472701831404]
  Retrieval-Augmented Text-to-Image Generator (Re-Imagen) Retrieval-Augmented Text-to-Image Generator (Re-Imagen)
  arXiv  Detail & Related papers  (2022-09-29T00:57:28Z)
• Progressive Learning for Image Retrieval with Hybrid-Modality Queries [48.79599320198615]
  Image retrieval with hybrid-modality queries, also known as composing text and image for image retrieval (CTI-IR) We decompose the CTI-IR task into a three-stage learning problem to progressively learn the complex knowledge for image retrieval with hybrid-modality queries. Our proposed model significantly outperforms state-of-the-art methods in the mean of Recall@K by 24.9% and 9.5% on the Fashion-IQ and Shoes benchmark datasets respectively.
  arXiv  Detail & Related papers  (2022-04-24T08:10:06Z)
• Probabilistic Compositional Embeddings for Multimodal Image Retrieval [48.450232527041436]
  We investigate a more challenging scenario for composing multiple multimodal queries in image retrieval. Given an arbitrary number of query images and (or) texts, our goal is to retrieve target images containing the semantic concepts specified in multiple multimodal queries. We propose a novel multimodal probabilistic composer (MPC) to learn an informative embedding that can flexibly encode the semantics of various queries.
  arXiv  Detail & Related papers  (2022-04-12T14:45:37Z)
• Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations [3.3754780158324564]
  Cross-modality image retrieval is challenging, since images of similar (or even the same) content captured by different modalities might share few common structures. We propose a new application-independent content-based image retrieval system for reverse (sub-)image search across modalities.
  arXiv  Detail & Related papers  (2022-01-10T19:04:28Z)

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.