mlsanityData to 7 Oct 2026

FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching

arXiv 2605.05077 ↗First posted 6 May 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

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

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

37 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity14 Oct

Other references · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2024GPT-4o System Cardcited by 4,467
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  11. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  12. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
24 more
  1. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  2. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  3. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  4. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 169
  5. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  6. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  7. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  8. 2019Towards High-Resolution Salient Object Detectioncited by 92
  9. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  10. 2016Deep Contrast Learning for Salient Object Detectioncited by 52
  11. 2023Exploiting Diffusion Prior for Generalizable Dense Predictioncited by 37
  12. 2022Revisiting Image Pyramid Structure for High Resolution Salient Object Detectioncited by 36
  13. 2021Disentangled High Quality Salient Object Detectioncited by 35
  14. 2024Multi-view Aggregation Network for Dichotomous Image Segmentationcited by 28
  15. 2023CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Modelscited by 21
  16. 2023Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentationcited by 17
  17. 2024Frontiers in Intelligent Colonoscopycited by 13
  18. 2025Training-Free Class Purification for Open-Vocabulary Semantic Segmentationcited by 9
  19. 2020Meticulous Object Segmentationcited by 8
  20. 2025Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspectivecited by 5
  21. 2025Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perceptioncited by 4
  22. 2025Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Drivingcited by 2
  23. 2025High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategycited by 1
  24. 2025LawDIS: Language-Window-based Controllable Dichotomous Image Segmentationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms
  2. 2024Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation
  3. 2024MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation
  4. 2025LatentFM: A Latent Flow Matching Approach for Generative Medical Image Segmentation
  5. 2026Rethinking Vector Field Learning for Generative Segmentation
  6. 2025Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
  7. 2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
  8. 2026D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation