MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

• URL: http://arxiv.org/abs/2505.19707v1
• Date: Mon, 26 May 2025 08:56:59 GMT
• Title: MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval
• Authors: Rong-Cheng Tu, Zhao Jin, Jingyi Liao, Xiao Luo, Yingjie Wang, Li Shen, Dacheng Tao,
• Abstract summary: Zero-Shot Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens.<n>We propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI) to construct two complementary training tasks using only unlabeled images.
• Score: 50.062817677022586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifying text and processed by frozen text encoders in pretrained VLMs or LLMs. While this design leverages the strengths of large pretrained models, it only supervises the adapter to produce encoder-compatible tokens that loosely preserve visual semantics. Crucially, it does not directly optimize the composed query representation to capture the full intent of the composition or to align with the target semantics, thereby limiting retrieval performance, particularly in cases involving fine-grained or complex visual transformations. To address this problem, we propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI), a novel approach that leverages a pretrained multimodal large language model (MLLM) to construct two complementary training tasks using only unlabeled images: target text retrieval taskand text-to-image retrieval task. By jointly optimizing these tasks, our method enables the VLM to inherently acquire robust compositional retrieval capabilities, supported by the provided theoretical justifications and empirical validation. Furthermore, during inference, we further prompt the MLLM to generate target texts from composed queries and compute retrieval scores by integrating similarities between (i) the composed query and candidate images, and (ii) the MLLM-generated target text and candidate images. This strategy effectively combines the VLM's semantic alignment strengths with the MLLM's reasoning capabilities.

Related papers

• Multimodal LLMs as Customized Reward Models for Text-to-Image Generation [60.164968941945645]
  We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives.<n>LLaVA-Reward directly utilizes the hidden states of multimodal large language models (MLLMs)<n>We train LLaVA-Reward on four evaluation perspectives: text-image alignment, fidelity/artifact, safety, and overall ranking.
  arXiv  Detail & Related papers  (2025-07-28T23:52:53Z)
• 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)
• From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs [23.011836329934255]
  Vision Dynamic Embedding-Guided Pretraining (VDEP) is a hybrid autoregressive training paradigm for MLLMs.<n>The proposed method seamlessly integrates into standard models without architectural changes.<n> Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods.
  arXiv  Detail & Related papers  (2025-02-13T09:04:28Z)
• PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures [5.513631883813244]
  We propose a framework that textbfPre-textbfIntegratestextbfPrompt information into the visual encoding process using existingmodules of MLLMs. Our model maintains excellent generation even when half of the visual tokens are reduced.
  arXiv  Detail & Related papers  (2024-10-30T15:05:17Z)
• SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization [70.11167263638562]
  Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. We first present a simple yet well-crafted framework named name, which combines the perception capability of Vision Foundation Models (VFMs) and the reasoning capability of Large Language Models (LLMs) within a modular framework.
  arXiv  Detail & Related papers  (2024-10-28T18:10:26Z)
• Large Language Models for Multimodal Deformable Image Registration [50.91473745610945]
  We propose a novel coarse-to-fine MDIR framework,LLM-Morph, for aligning the deep features from different modal medical images. Specifically, we first utilize a CNN encoder to extract deep visual features from cross-modal image pairs, then we use the first adapter to adjust these tokens, and use LoRA in pre-trained LLMs to fine-tune their weights. Third, for the alignment of tokens, we utilize other four adapters to transform the LLM-encoded tokens into multi-scale visual features, generating multi-scale deformation fields and facilitating the coarse-to-fine MDIR task
  arXiv  Detail & Related papers  (2024-08-20T09:58:30Z)
• MATE: Meet At The Embedding -- Connecting Images with Long Texts [37.27283238166393]
  Meet At The Embedding (MATE) is a novel approach that combines the capabilities of Large Language Models (LLMs) with Vision Language Models (VLMs) We replace the text encoder of the VLM with a pretrained LLM-based encoder that excels in understanding long texts. We propose two new cross-modal retrieval benchmarks to assess the task of connecting images with long texts.
  arXiv  Detail & Related papers  (2024-06-26T14:10:00Z)
• Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex [4.57590454144072]
  Recently, there has been a surge in the popularity of pre trained large language models (LLMs) This paper proposes a new multi-modal training paradigm, aligning with LLM, encoding fMRI activity in visual cortex.
  arXiv  Detail & Related papers  (2024-01-08T12:30:23Z)
• LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation [51.08810811457617]
  vision-language alignment in LLMs is actively being researched to enable multimodal reasoning and visual IO. We develop a method for instruction-tuning an LLM only on text to gain vision-language capabilities for medical images. Our model, LLM-CXR, trained in this approach shows better image-text alignment in both CXR understanding and generation tasks.
  arXiv  Detail & Related papers  (2023-05-19T07:44:39Z)

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.