cs.CVNov 4, 2026

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

Authors: Hongyu Cao, Guangfu Guo, Jinghan Zhang, Dakshak Keerthi Chandra, Ying Zhang, Kunpeng Liu

Organizations: Clemson University, Clemson, SC, USA · Analog Devices, Inc., USA · Wake Forest University, USA

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.

Figures & tables

Explore similar work

CardsList
  1. DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image Classification

    Mar 17, 2026Stathis Galanakis, Alexandros Koliousis, Stefanos ZafeiriouMedical Image SynthesisSynthetic Data Augmentation

  2. InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation

    Sep 2, 2026Ziquan Liu, Zhewei Zhu, Xuyang ShiText-Guided Image SegmentationPolyp Segmentation

  3. Privileged Lesion-Context Relational Distillation for Mask-Free Skin Lesion Classification

    Jul 21, 2026Abu Mukaddim Rahi, Md Mithun Hossain, Md Zulficar Hasan Joy +2Skin Lesion ClassificationMedical Image Classification