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

arXiv: https://arxiv.org/abs/2606.27794 · HTML: https://mlsanity.com/paper/2606.27794/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [LViT: Language meets Vision Transformer in Medical Image Segmentation](https://mlsanity.com/paper/2206.14718/) (2022)
- [TGANet: Text-guided attention for improved polyp segmentation](https://mlsanity.com/paper/2205.04280/) (2022)
- [OSegNet: Operational Segmentation Network for COVID-19 Detection using Chest X-ray Images](https://mlsanity.com/paper/2202.10185/) (2022)
- [Ariadne's Thread:Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images](https://mlsanity.com/paper/2307.03942/) (2023)
- [Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation](https://mlsanity.com/paper/2404.02845/) (2024)
- [Multi-modal Vision Pre-training for Medical Image Analysis](https://mlsanity.com/paper/2410.10604/) (2024)
- [SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation](https://mlsanity.com/paper/2406.14896/) (2024)
- [TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Images](https://mlsanity.com/paper/2310.14214/) (2023)
- [Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation](https://mlsanity.com/paper/2208.06283/) (2022)

## Abstract (arXiv)

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.