Training-Free Pseudo-Fusion for Composed Image Retrieval with Diffusion Models and Multimodal Large Language Models

• URL: http://arxiv.org/abs/2608.23102v1
• Date: Mon, 24 Aug 2026 11:08:28 GMT
• Title: Training-Free Pseudo-Fusion for Composed Image Retrieval with Diffusion Models and Multimodal Large Language Models
• Abstract summary: Composed Image Retrieval (CIR) is an emerging paradigm in content-based image retrieval.<n>In this work, we propose PeFuse, a training-free framework that leverages pretrained Diffusion Models and Multimodal Large Language Models.<n>We introduce two novel strategies: uni-directional and bi-directional conversion, which convert CIR into four single-modality retrieval problems.
• Score: 10.421702262520775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Composed Image Retrieval (CIR) is an emerging paradigm in content-based image retrieval that enables users to formulate compositional queries by combining a reference image with an auxiliary modality, usually text-based. This approach supports fine-grained search where the target image shares structural elements with the user-provided image while incorporating the modifications specified by the auxiliary text. Conventional CIR methods rely on multimodal fusion to combine visual and textual features into a joint query embedding, which requires training modules that align composed queries with the targets. In this work, we propose PeFuse (for pseudo-fusion), a training-free framework that leverages pretrained Diffusion Models and Multimodal Large Language Models to bridge modalities via generative conversion. We introduce two novel strategies: uni-directional and bi-directional conversion, which convert CIR into four single-modality retrieval problems. These methods reformulate CIR as either intra-modal or cross-modal single-query retrieval tasks, bypassing the need for dedicated task-specific training. Extensive experiments on standard benchmarks demonstrate that converting CIR into text-to-image retrieval tasks is more effective than alternative conversion strategies, achieving competitive or superior performance compared with state-of-the-art methods, while maintaining high flexibility thanks to replaceable components of the conversion pipeline. These results highlight the effectiveness of the pseudo-fusion paradigm for zero-shot CIR. Our code is publicly available at: https://github.com/StevenXuf/PeFuse4CIR.

Related papers

• Do Composed Image Retrieval Benchmarks Require Multimodal Composition? [86.99911649534795]
  We show that strong performance on Composed Image Retrieval benchmarks is assumed to require multimodal composition.<n>Across four widely used CIR benchmarks and eleven Generalist Multimodal Embedding models, a large fraction of queries can be solved using a single modality.<n>High CIR performance can arise from unimodal signals rather than true multimodal composition.
  arXiv  Detail & Related papers  (2026-05-14T12:56:36Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• Recurrence Meets Transformers for Universal Multimodal Retrieval [59.92546492752452]
  ReT-2 is a unified retrieval model that supports multimodal queries composed of both images and text.<n>We evaluate ReT-2 on the challenging M2KR and M-BEIR benchmarks across different retrieval configurations.<n>When integrated into retrieval-augmented generation pipelines, ReT-2 also improves downstream performance on Encyclopedic-VQA and InfoSeek datasets.
  arXiv  Detail & Related papers  (2025-09-10T18:00:29Z)
• CoLLM: A Large Language Model for Composed Image Retrieval [76.29725148964368]
  Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query.<n>We present CoLLM, a one-stop framework that generates triplets on-the-fly from image-caption pairs.<n>We leverage Large Language Models (LLMs) to generate joint embeddings of reference images and modification texts.
  arXiv  Detail & Related papers  (2025-03-25T17:59:50Z)
• Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval [44.008094698200026]
  Cross-modal retrieval is gaining increasing efficacy and interest from the research community.<n>In this paper, we design an approach that allows for multimodal queries composed of both an image and a text.<n>Our model, ReT, employs multi-level representations extracted from different layers of both visual and textual backbones.
  arXiv  Detail & Related papers  (2025-03-03T19:01:17Z)
• 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)
• Compositional Image Retrieval via Instruction-Aware Contrastive Learning [40.54022628032561]
  Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference.<n>In practice, due to the scarcity of annotated data in downstream tasks, Zero-Shot CIR (ZS-CIR) is desirable.<n>We propose a novel embedding method utilizing an instruction-tuned Multimodal LLM (MLLM) to generate composed representation.
  arXiv  Detail & Related papers  (2024-12-07T22:46:52Z)
• Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval [20.612534837883892]
  Zero-Shot Composed Image Retrieval (ZS-CIR) is designed to retrieve target images using bi-modal (image+text) queries.<n>We propose a lightweight post-hoc framework, consisting of two components.<n>Experiments show that, with the incorporation of our proposed components, inversion-based methods achieve significant improvements.
  arXiv  Detail & Related papers  (2024-10-31T08:49:05Z)
• Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity [2.724141845301679]
  Composed image retrieval (CIR) formulates the query as a combination of a reference image and modified text. We introduce a training-free approach for ZS-CIR. Our approach is simple, easy to implement, and its effectiveness is validated through experiments on the FashionIQ and CIRR datasets.
  arXiv  Detail & Related papers  (2024-09-07T21:52:58Z)
• Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval [80.35589927511667]
  Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. We propose a novel fine-tuning framework which turns any pretrained text-image multi-modal model into an efficient retrieval model. Our experiments on a series of standard cross-modal retrieval benchmarks in monolingual, multilingual, and zero-shot setups, demonstrate improved accuracy and huge efficiency benefits over the state-of-the-art cross-encoders.
  arXiv  Detail & Related papers  (2021-03-22T15:08:06Z)

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.