CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling

• URL: http://arxiv.org/abs/2406.17507v2
• Date: Tue, 15 Jul 2025 03:20:06 GMT
• Title: CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling
• Authors: Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao,
• Abstract summary: Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
• Score: 53.97609687516371
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates, which is challenged by training cost and inference latency with large-scale data. Inspired by the remarkable performance and efficiency of generative models, we propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling, which assigns identifiers to each candidate and treats the generating identifier as the retrieval target. Specifically, we explore an effective coarse-to-fine scheme, combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation. Further, considering the lack of explicit interaction between queries and candidates, we propose a feature fusion strategy to align their semantics. Extensive experiments demonstrate the effectiveness of the strategies in the CART, achieving excellent results in both retrieval performance and efficiency.

Related papers

• SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs [70.79124435220695]
  We propose a novel unified Semantic-enhanced generative Cross-mOdal REtrieval framework (SemCORE) We first construct a Structured natural language IDentifier (SID) that effectively aligns target identifiers with generative models optimized for natural language comprehension and generation. We then introduce a Generative Semantic Verification (GSV) strategy enabling fine-grained target discrimination.
  arXiv  Detail & Related papers  (2025-04-17T17:59:27Z)
• Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts [67.67746334493302]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks. We propose a tri-encoder sequential retriever that models this process as a Markov Decision Process (MDP) We show that our method consistently and significantly outperforms baselines, underscoring the importance of explicitly modeling inter-example dependencies.
  arXiv  Detail & Related papers  (2025-04-15T17:35:56Z)
• 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. At its core, GENIUS introduces modality-decoupled semantic quantization, transforming multimodal data into discrete IDs encoding both modality and semantics. 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)
• MultiConIR: Towards multi-condition Information Retrieval [57.6405602406446]
  We introduce MultiConIR, the first benchmark designed to evaluate retrieval models in multi-condition scenarios.<n>We propose three tasks to assess retrieval and reranking models on multi-condition robustness, monotonic relevance ranking, and query format sensitivity.
  arXiv  Detail & Related papers  (2025-03-11T05:02:03Z)
• HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs [0.3277163122167434]
  This paper introduces HEISIR, a novel framework that enhances semantic understanding in conversational data retrieval. Heisir implements a two-step process: (1) Hierarchical Triplets Formulation and (2) Adjunct Augmentation, creating semantic indices consisting of Subject-Verb-Object-Adjunct (SVOA) quadruplets. Our experimental results demonstrate that HEISIR outperforms fine-tuned models across various embedding types and language models.
  arXiv  Detail & Related papers  (2025-03-06T06:39:25Z)
• Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations [22.48125906976824]
  We introduce the Cascaded Organized Bi-Represented generAtive retrieval framework, which integrates sparse semantic IDs and dense vectors through a cascading process.<n>Our method alternates between generating these representations by first generating sparse IDs, which serve as conditions to aid in the generation of dense vectors.<n>During inference, COBRA employs a coarse-to-fine strategy, starting with sparse ID generation and refining them into dense vectors via the generative model.
  arXiv  Detail & Related papers  (2025-03-04T10:00:05Z)
• Re-ranking the Context for Multimodal Retrieval Augmented Generation [28.63893944806149]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context. RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate
  arXiv  Detail & Related papers  (2025-01-08T18:58:22Z)
• A Distributed Collaborative Retrieval Framework Excelling in All Queries and Corpora based on Zero-shot Rank-Oriented Automatic Evaluation [46.33857318525812]
  We propose a novel Distributed Collaborative Retrieval Framework (DCRF)<n>It integrates various retrieval models into a unified system and dynamically selects the optimal results for each user's query.<n>It can achieve performance comparable to effective listwise methods like RankGPT and ListT5.
  arXiv  Detail & Related papers  (2024-12-16T14:55:57Z)
• GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning [51.677086019209554]
  We propose a Generalized Structural Sparse to capture powerful relationships across modalities for pair-wise similarity learning. The distance metric delicately encapsulates two formats of diagonal and block-diagonal terms. Experiments on cross-modal and two extra uni-modal retrieval tasks have validated its superiority and flexibility.
  arXiv  Detail & Related papers  (2024-10-20T03:45:50Z)
• Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
  We introduce a framework called GRaded Generative Retrieval (GR$2$) GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
  arXiv  Detail & Related papers  (2024-09-27T02:55:53Z)
• Generative Retrieval with Preference Optimization for E-commerce Search [16.78829577915103]
  We develop an innovative framework for E-commerce search, called generative retrieval with preference optimization. We employ multi-span identifiers to represent raw item titles and transform the task of generating titles from queries into the task of generating multi-span identifiers from queries. Our experiments show that this framework achieves competitive performance on a real-world dataset, and online A/B tests demonstrate the superiority and effectiveness in improving conversion gains.
  arXiv  Detail & Related papers  (2024-07-29T09:31:19Z)
• Multi-Modal Retrieval For Large Language Model Based Speech Recognition [15.494654232953678]
  We propose multi-modal retrieval with two approaches: kNN-LM and cross-attention techniques. We show that speech-based multi-modal retrieval outperforms text based retrieval. We achieve state-of-the-art recognition results on the Spoken-Squad question answering dataset.
  arXiv  Detail & Related papers  (2024-06-13T22:55:22Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)
• Recommender Systems with Generative Retrieval [58.454606442670034]
  We propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful of codewords to serve as a Semantic ID for each item. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets.
  arXiv  Detail & Related papers  (2023-05-08T21:48:17Z)
• Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval [152.3504607706575]
  This research aims to conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and define two real practical instance-level retrieval tasks. We exploit to train a more effective cross-modal model which is adaptively capable of incorporating key concept information from the multi-modal data.
  arXiv  Detail & Related papers  (2022-06-17T15:40:45Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• Unsupervised Contrastive Hashing for Cross-Modal Retrieval in Remote Sensing [1.6758573326215689]
  Cross-modal text-image retrieval has attracted great attention in remote sensing. We introduce a novel unsupervised cross-modal contrastive hashing (DUCH) method for text-image retrieval in RS. Experimental results show that the proposed DUCH outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-19T07:25:25Z)
• Efficient Data-specific Model Search for Collaborative Filtering [56.60519991956558]
  Collaborative filtering (CF) is a fundamental approach for recommender systems. In this paper, motivated by the recent advances in automated machine learning (AutoML), we propose to design a data-specific CF model. Key here is a new framework that unifies state-of-the-art (SOTA) CF methods and splits them into disjoint stages of input encoding, embedding function, interaction and prediction function.
  arXiv  Detail & Related papers  (2021-06-14T14:30:32Z)
• 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.