Text as Illumination: Spatial Contrastive Retinex Learning for Language-guided Medical Image Segmentation

• URL: http://arxiv.org/abs/2606.27794v1
• Date: Fri, 26 Jun 2026 07:27:48 GMT
• Title: Text as Illumination: Spatial Contrastive Retinex Learning for Language-guided Medical Image Segmentation
• Abstract summary: Language-guided Medical Image (LMIS) has shown great potential to improve the delineation of anatomical structures and lesions.<n> Existing methods rely on either implicit interaction between textual and visual features or auxiliary coarse-grained supervision for cross-modal alignment.<n>We propose Text-as-Illumination Retinex Network (TIRNet), a novel framework that treats text embeddings as semantic illumination for feature modulation.
• Score: 81.21550084361755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language-guided Medical Image Segmentation (LMIS) has shown great potential to improve the delineation of anatomical structures and lesions by integrating clinical textual information. Existing methods generally rely on either implicit interaction between textual and visual features or auxiliary coarse-grained supervision for cross-modal alignment. However, these methods lack explicit and fine-grained constraints to ensure semantic consistency, causing a mismatch between language and the segmentation outputs. To address this issue, we propose Text-as-Illumination Retinex Network (TIRNet), a novel Retinex-inspired framework that treats text embeddings as semantic illumination for feature modulation, thereby improving semantic consistency in LMIS. TIRNet introduces two key blocks integrated at each decoder stage: (1) the Retinex-inspired Text Modulation Block (RTMB), which employs positive and negative illumination maps to enhance text-relevant foreground features and suppress background interference; and (2) the Consistent Detail Compensation Block (CDCB), which selectively recovers high-frequency details via a consistency-gated mechanism conditioned on illumination reliability. Furthermore, we propose a Multi-Scale Illumination Supervision Loss (MSIS-Loss), comprising a Region-Grounded Contrastive Loss (RGC-Loss) that enforces cross-modal similarity to be concentrated in text-relevant foreground regions and suppressed in background regions, and a Background Suppression Loss (BS-Loss) that provides pixel-level supervision for negative illumination maps, jointly ensuring a precise cross-modal alignment at each decoder stage. Extensive experiments on the MosMedData+ and QaTa-COV19 datasets demonstrate that TIRNet achieves state-of-the-art performance in LMIS. The code is available at: https://github.com/anaanaa/TIRNet.

Related papers

• Text-guided Feature Disentanglement for Cross-modal Gait Recognition [5.766298616867406]
  Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios.<n>Real-world scenarios often involve sensing modalities such as LiDAR and RGB cameras, making LiDAR-Cross-modal Gait recognition a critical yet challenging task.<n>To address this challenge, we propose TCFDNet, a Text-guided Cross-modal Feature Disentanglement Network.<n>Extensive experiments on SUSTech1K and FreeGait datasets demonstrate that TCFDNet achieves new state-of-the-art results and validate the effectiveness of the proposed modules.
  arXiv  Detail & Related papers  (2026-05-29T03:16:44Z)
• Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment [34.61027348260765]
  Semi-supervised learning (SSL) can mitigate this burden by leveraging unlabeled data.<n>We propose Semi-MedRef, a teacher-student SSL framework designed to explicitly maintain consistency between medical images and positional language.<n> Experiments on QaTa-COV19 and MosMedData+ demonstrate that Semi-MedRef consistently outperforms both fully supervised and semi-supervised baselines.
  arXiv  Detail & Related papers  (2026-05-15T08:15:45Z)
• FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement [21.260231526776128]
  We propose FB-CLIP, a framework that enhances anomaly localization via multi-strategy textual representations and foreground-background separation.<n>Experiments show that FB-CLIP effectively distinguishes anomalies from complex backgrounds, achieving accurate fine-grained anomaly detection and localization under zero-shot settings.
  arXiv  Detail & Related papers  (2026-03-20T03:25:56Z)
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning [59.013863248600046]
  We propose a spatially re-focused super-resolution framework that refines text conditioning at inference time.<n>Second, we introduce a Spatially Targeted-Free Guidance mechanism that selectively bypasses text influences on ungrounded pixels to prevent hallucinations.
  arXiv  Detail & Related papers  (2025-10-26T05:03:55Z)
• XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning [0.0]
  XBusNet is a novel dual-prompt, dual-branch multimodal model that combines image features with clinically grounded text.<n>We evaluate it on the Breast Lesions USG (BLU) dataset using five-fold cross-validation.<n>Small lesions show the largest gains, with fewer missed regions and fewer spurious activations.
  arXiv  Detail & Related papers  (2025-09-08T20:45:55Z)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• Data-Efficient Generalization for Zero-shot Composed Image Retrieval [67.46975191141928]
  ZS-CIR aims to retrieve the target image based on a reference image and a text description without requiring in-distribution triplets for training.<n>One prevalent approach follows the vision-language pretraining paradigm that employs a mapping network to transfer the image embedding to a pseudo-word token in the text embedding space.<n>We propose a Data-efficient Generalization (DeG) framework, including two novel designs, namely, Textual Supplement (TS) module and Semantic-Set (S-Set)
  arXiv  Detail & Related papers  (2025-03-07T07:49:31Z)
• 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)
• What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation [16.033361754660316]
  Notice is the first Noise-free Text-Image Corruption and Evaluation pipeline for interpretability in Vision-Language Models (VLMs)<n>Our experiments on the SVO-Probes, MIT-States, and Facial Expression Recognition datasets reveal crucial insights into VLM decision-making.<n>This work paves the way for more transparent and interpretable multimodal systems.
  arXiv  Detail & Related papers  (2024-06-24T05:13:19Z)
• Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search [61.24539128142504]
  Text-based person search (TBPS) is a challenging task that aims to search pedestrian images with the same identity from an image gallery given a query text. Most existing methods rely on explicitly generated local parts to model fine-grained correspondence between modalities. We propose an efficient joint Multi-level Alignment Network (MANet) for TBPS, which can learn aligned image/text feature representations between modalities at multiple levels.
  arXiv  Detail & Related papers  (2022-08-30T16:14:18Z)

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.