SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment

• URL: http://arxiv.org/abs/2511.01390v1
• Date: Mon, 03 Nov 2025 09:41:32 GMT
• Title: SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
• Authors: Xinyu Mao, Junsi Li, Haoji Zhang, Yu Liang, Ming Sun,
• Abstract summary: We introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity.<n>Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches.<n>Experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance.
• Score: 8.657941729790599
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23\%-86\% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.

Related papers

• Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models [84.78794648147608]
  A persistent geometric anomaly, the Modality Gap, remains.<n>Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions.<n>We propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap into stable biases and anisotropic residuals.<n>We then introduce ReAlign, a training-free modality alignment strategy.
  arXiv  Detail & Related papers  (2026-02-02T13:59:39Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation [8.48847068018671]
  This paper proposes TFANet, a Three-stage Image-Text Feature Alignment Network.<n>It enhances multimodal alignment through a hierarchical framework comprising three stages: Knowledge Plus Stage (KPS), Knowledge Fusion Stage (KFS), and Knowledge Intensification Stage (KIS)<n>In the KPS, we design the Multiscale Linear Cross-Attention Module (MLAM), which establishes rich and efficient alignment between image regions and different granularities of linguistic descriptions.<n>The KFS further strengthens feature alignment through the Cross-modal Feature Scanning Module (CFSM), which applies multimodal selective scanning to capture long-range dependencies
  arXiv  Detail & Related papers  (2025-09-16T13:26:58Z)
• MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces [23.447713697204225]
  MAGE is a novel framework that bridges the semantic spaces of vision and text through an innovative alignment mechanism.<n>We employ a training strategy that combines cross-entropy and mean squared error, significantly enhancing the alignment effect.<n>Our proposed multimodal large model architecture, MAGE, achieved significantly better performance compared to similar works across various evaluation benchmarks.
  arXiv  Detail & Related papers  (2025-07-29T12:17:46Z)
• Visual Semantic Description Generation with MLLMs for Image-Text Matching [7.246705430021142]
  We propose a novel framework that bridges the modality gap by leveraging multimodal large language models (MLLMs) as visual semantics.<n>Our approach combines: (1) Instance-level alignment by fusing visual features with VSD to enhance the linguistic expressiveness of image representations, and (2) Prototype-level alignment through VSD clustering to ensure category-level consistency.
  arXiv  Detail & Related papers  (2025-07-11T13:38:01Z)
• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [50.433911327489554]
  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.<n>To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM)<n>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)
• Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval [40.83470534691711]
  Cross-lingual cross-modal retrieval ( CCR) aims to retrieve visually relevant content based on non-English queries. One popular approach involves utilizing machine translation (MT) to create pseudo-parallel data pairs. We propose LE CCR, a novel solution that incorporates the multi-modal large language model (MLLM) to improve the alignment between visual and non-English representations.
  arXiv  Detail & Related papers  (2024-09-30T05:25:51Z)
• Spatial Semantic Recurrent Mining for Referring Image Segmentation [63.34997546393106]
  We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-05-15T00:17:48Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• SCMM: Calibrating Cross-modal Representations for Text-Based Person Search [45.24784242117999]
  Text-Based Person Search (TBPS) faces critical challenges in cross-modal information fusion.<n>We propose SCMM (Sew and Masked Modeling), a novel framework addressing these fusion challenges through two complementary mechanisms.
  arXiv  Detail & Related papers  (2023-04-05T07:50:16Z)
• Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens [76.40196364163663]
  We propose a learning-based vision-language pre-training approach, such as CLIP. We show that our method can learn more comprehensive representations and capture meaningful cross-modal correspondence.
  arXiv  Detail & Related papers  (2023-03-27T00:58:39Z)

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.