# FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching

arXiv: https://arxiv.org/abs/2605.05077 · HTML: https://mlsanity.com/paper/2605.05077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Towards High-Resolution Salient Object Detection](https://mlsanity.com/paper/1908.07274/) (2019)
- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [Deep Contrast Learning for Salient Object Detection](https://mlsanity.com/paper/1603.01976/) (2016)
- [Exploiting Diffusion Prior for Generalizable Dense Prediction](https://mlsanity.com/paper/2311.18832/) (2023)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [Disentangled High Quality Salient Object Detection](https://mlsanity.com/paper/2108.03551/) (2021)
- [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024)
- [CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models](https://mlsanity.com/paper/2305.17932/) (2023)
- [Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation](https://mlsanity.com/paper/2307.14052/) (2023)
- [Frontiers in Intelligent Colonoscopy](https://mlsanity.com/paper/2410.17241/) (2024)
- [Training-Free Class Purification for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2508.00557/) (2025)

## Abstract (arXiv)

Accurate image segmentation is essential for modern computer vision applications such as image editing, autonomous driving, and medical image analysis. In recent years, Dichotomous Image Segmentation (DIS) has become a standard task for training and evaluating highly accurate segmentation models. Existing DIS approaches often fail to preserve fine-grained details or fully capture the semantic structure of the foreground. To address these challenges, we present FlowDIS, a novel dichotomous image segmentation method built on the flow matching framework, which learns a time-dependent vector field to transport the image distribution to the corresponding mask distribution, optionally conditioned on a text prompt. Moreover, with our Position-Aware Instance Pairing (PAIP) training strategy, FlowDIS offers strong controllability through text prompts, enabling precise, pixel-level object segmentation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches both with and without language guidance. Compared with the best prior DIS method, FlowDIS achieves a 5.5% higher Fβω measure and 43% lower MAE (M) on the DIS-TE test set. The code is available at: https://github.com/Picsart-AI-Research/FlowDIS