Skip to content
AI News HubLIVE
Original source2 min read

Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation

Summary

Researchers propose GENIQ, a training-free method that leverages images generated by a text-to-image diffusion transformer to construct skin and lesion prototypes, refined on unlabeled dermoscopy images for skin lesion segmentation. It achieves Dice scores of 0.85-0.88 on three test sets, outperforming zero-shot and word-based attention methods.

SourcearXiv Computer VisionAuthor: Hongyu Cao, Guangfu Guo, Jinghan Zhang, Dakshak Keerthi Chandra, Ying Zhang, Kunpeng Liu
Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 4 Nov 2026]

Title:Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation

View a PDF of the paper titled Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation, by Hongyu Cao and 5 other authors

View PDF HTML (experimental)

Abstract:Skin lesion segmentation without annotated masks requires the target to be specified through other cues. Existing approaches rely on dermoscopy-specific rules, annotation-derived model priors, or user-selected regions. A general text-to-image diffusion transformer offers a text interface to the target, but its concept-word attention is unreliable on dermoscopy images: in the model's attention-output space, the word-derived skin-to-lesion direction is poorly aligned with the direction separating real skin from real lesions. We show that the direction derived from generated healthy-skin and lesion images is substantially better aligned. Based on this finding, we propose GENIQ, a training-free method that constructs initial skin and lesion prototypes from generated images and refines them using the most skin-like and lesion-like patches from unlabelled dermoscopy images. It scores test patches along the refined direction and applies a gated threshold to suppress contextual spill-over around small lesions. Without inference-time annotations or additional models, GENIQ achieves Dice scores of 0.85-0.88 on three dermoscopy test sets. It outperforms zero-shot and word-based attention methods on all three sets, and a hand-designed dermoscopy pipeline in Dice and IoU on two.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

ACM classes: I.4.6; I.2.10

Cite as: arXiv:2611.07061 [cs.CV]

(or arXiv:2611.07061v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.07061

arXiv-issued DOI via DataCite

Submission history

From: Hongyu Cao [view email] [v1] Wed, 4 Nov 2026 19:20:08 UTC (643 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation, by Hongyu Cao and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • GENIQ uses generated images rather than concept words to define the skin-to-lesion direction, as text attention is unreliable on dermoscopy images.
  • The method is training-free and requires no inference-time annotations or additional models; it builds initial prototypes from generated images and refines them using the most skin-like and lesion-like patches from unlabeled images.
  • It achieves Dice scores of 0.85-0.88 on three dermoscopy test sets, surpassing zero-shot and word-based attention methods, and outperforms a hand-designed dermoscopy pipeline on two sets.
  • A gated threshold suppresses contextual spill-over around small lesions, improving segmentation accuracy.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models

Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation | AI News Hub