SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs

• URL: http://arxiv.org/abs/2504.13172v1
• Date: Thu, 17 Apr 2025 17:59:27 GMT
• Title: SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs
• Authors: Haoxuan Li, Yi Bin, Yunshan Ma, Guoqing Wang, Yang Yang, See-Kiong Ng, Tat-Seng Chua,
• Abstract summary: We propose a novel unified Semantic-enhanced generative Cross-mOdal REtrieval framework (SemCORE)<n>We first construct a Structured natural language IDentifier (SID) that effectively aligns target identifiers with generative models optimized for natural language comprehension and generation.<n>We then introduce a Generative Semantic Verification (GSV) strategy enabling fine-grained target discrimination.
• Score: 70.79124435220695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-modal retrieval (CMR) is a fundamental task in multimedia research, focused on retrieving semantically relevant targets across different modalities. While traditional CMR methods match text and image via embedding-based similarity calculations, recent advancements in pre-trained generative models have established generative retrieval as a promising alternative. This paradigm assigns each target a unique identifier and leverages a generative model to directly predict identifiers corresponding to input queries without explicit indexing. Despite its great potential, current generative CMR approaches still face semantic information insufficiency in both identifier construction and generation processes. To address these limitations, we propose a novel unified Semantic-enhanced generative Cross-mOdal REtrieval framework (SemCORE), designed to unleash the semantic understanding capabilities in generative cross-modal retrieval task. Specifically, we first construct a Structured natural language IDentifier (SID) that effectively aligns target identifiers with generative models optimized for natural language comprehension and generation. Furthermore, we introduce a Generative Semantic Verification (GSV) strategy enabling fine-grained target discrimination. Additionally, to the best of our knowledge, SemCORE is the first framework to simultaneously consider both text-to-image and image-to-text retrieval tasks within generative cross-modal retrieval. Extensive experiments demonstrate that our framework outperforms state-of-the-art generative cross-modal retrieval methods. Notably, SemCORE achieves substantial improvements across benchmark datasets, with an average increase of 8.65 points in Recall@1 for text-to-image retrieval.

Related papers

• GENIUS: A Generative Framework for Universal Multimodal Search [26.494338650656594]
  This paper proposes GENIUS, a universal generative retrieval framework supporting diverse tasks across multiple modalities and domains.<n>At its core, GENIUS introduces modality-decoupled semantic quantization, transforming multimodal data into discrete IDs encoding both modality and semantics.<n>To enhance generalization, we propose a query augmentation that interpolates between a query and its target, allowing GENIUS to adapt to varied query forms.
  arXiv  Detail & Related papers  (2025-03-25T17:32:31Z)
• IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification [60.38841251693781]
  We propose a novel framework to generate robust multi-modal object ReIDs. Our framework uses Modal Prefixes and InverseNet to integrate multi-modal information with semantic guidance from inverted text. Experiments on three multi-modal object ReID benchmarks demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2025-03-13T13:00:31Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [9.109484087832058]
  The goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression. To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM) To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets.
  arXiv  Detail & Related papers  (2024-10-11T08:28:04Z)
• ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  We propose a pioneering generAtive Cross-modal rEtrieval framework (ACE) for end-to-end cross-modal retrieval. ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• 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)
• Language Models As Semantic Indexers [78.83425357657026]
  We introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval.
  arXiv  Detail & Related papers  (2023-10-11T18:56:15Z)
• Learning to Rank in Generative Retrieval [62.91492903161522]
  Generative retrieval aims to generate identifier strings of relevant passages as the retrieval target. We propose a learning-to-rank framework for generative retrieval, dubbed LTRGR. This framework only requires an additional learning-to-rank training phase to enhance current generative retrieval systems.
  arXiv  Detail & Related papers  (2023-06-27T05:48:14Z)
• GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback [8.142861977776256]
  We propose a novel approach which effectively integrates text generation models into PRF-based query expansion. Our approach generates augmented query terms via neural text generation models conditioned on both the initial query and pseudo-relevance feedback. We evaluate the performance of our approach on information retrieval tasks using two benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-13T01:09:02Z)

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.