Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation

• URL: http://arxiv.org/abs/2509.08570v1
• Date: Wed, 10 Sep 2025 13:16:30 GMT
• Title: Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
• Authors: Wenjun Yu, Yinchen Zhou, Jia-Xuan Jiang, Shubin Zeng, Yuee Li, Zhong Wang,
• Abstract summary: We propose an Expectation-Maximization (EM) Aggregation mechanism and a Text-Guided Pixel Decoder.<n>The latter is designed to bridge the semantic gap by leveraging domain-invariant textual knowledge to effectively guide deep visual representations.<n>Our method consistently outperforms existing SOTA approaches across multiple domain generalization benchmarks.
• Score: 5.597576681565333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal fusion, primarily the significant semantic gap between abstract textual prompts and fine-grained medical visual features, as well as the resulting feature dispersion. To address these issues, we revisit the problem from the perspective of semantic aggregation. Specifically, we propose an Expectation-Maximization (EM) Aggregation mechanism and a Text-Guided Pixel Decoder. The former mitigates feature dispersion by dynamically clustering features into compact semantic centers to enhance cross-modal correspondence. The latter is designed to bridge the semantic gap by leveraging domain-invariant textual knowledge to effectively guide deep visual representations. The synergy between these two mechanisms significantly improves the model's generalization ability. Extensive experiments on public cardiac and fundus datasets demonstrate that our method consistently outperforms existing SOTA approaches across multiple domain generalization benchmarks.

Related papers

• 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)
• Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms [16.699205051836657]
  Single-source domain generalization aims to learn a model from a single source domain that can generalize well on unseen target domains. This is an important task in computer vision, particularly relevant to medical imaging where domain shifts are common. We combine causality-inspired theoretical insights on learning domain-invariant representations with recent advancements in diffusion-based augmentation to improve generalization across diverse imaging modalities.
  arXiv  Detail & Related papers  (2024-11-07T22:35:17Z)
• Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation [54.96563068182733]
  We propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task. MADM utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities. We show that MADM achieves state-of-the-art adaptation performance across various modality tasks, including images to depth, infrared, and event modalities.
  arXiv  Detail & Related papers  (2024-10-29T03:49:40Z)
• Diffusion Features to Bridge Domain Gap for Semantic Segmentation [2.8616666231199424]
  This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently. By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it.
  arXiv  Detail & Related papers  (2024-06-02T15:33:46Z)
• Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System [22.331591533400402]
  Infrared and visible image fusion (IVF) plays an important role in intelligent transportation system (ITS) We propose a novel prior semantic guided image fusion method based on the dual-modality strategy.
  arXiv  Detail & Related papers  (2024-03-24T16:41:50Z)
• Enhancing Multimodal Unified Representations for Cross Modal Generalization [52.16653133604068]
  We propose Training-free Optimization of Codebook (TOC) and Fine and Coarse cross-modal Information Disentangling (FCID)<n>These methods refine the unified discrete representations from pretraining and perform fine- and coarse-grained information disentanglement tailored to the specific characteristics of each modality.
  arXiv  Detail & Related papers  (2024-03-08T09:16:47Z)
• On the Multi-modal Vulnerability of Diffusion Models [56.08923332178462]
  We propose MMP-Attack to manipulate the generation results of diffusion models by appending a specific suffix to the original prompt.<n>Our goal is to induce diffusion models to generate a specific object while simultaneously eliminating the original object.
  arXiv  Detail & Related papers  (2024-02-02T12:39:49Z)
• Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation [5.3590650005818254]
  We introduce the innovative Spectral Correlation Coefficient objective to improve the model's capacity to capture middle-order features and contextual long-range dependencies. Experiments reveal that optimizing this objective with existing architectures like UNet and TransUNet significantly enhances generalization, interpretability, and noise robustness.
  arXiv  Detail & Related papers  (2024-01-18T20:43:43Z)
• From Text to Pixels: A Context-Aware Semantic Synergy Solution for Infrared and Visible Image Fusion [66.33467192279514]
  We introduce a text-guided multi-modality image fusion method that leverages the high-level semantics from textual descriptions to integrate semantics from infrared and visible images. Our method not only produces visually superior fusion results but also achieves a higher detection mAP over existing methods, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2023-12-31T08:13:47Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)

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.