分割
计算机科学
人工智能
图像分割
模式识别(心理学)
钥匙(锁)
可靠性(半导体)
生成语法
猪皮
组分(热力学)
计算机视觉
皮肤损伤
尺度空间分割
机器学习
蒸馏
相似性(几何)
还原(数学)
生成模型
基于分割的对象分类
边界(拓扑)
图像(数学)
作者
Viet-Hoang Doan,Thanh-Danh Nguyen,Tuan-Kiet Ngo,Vinh-Tiep Nguyen
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-12-18
卷期号:: 90-95
标识
DOI:10.1109/rivf68649.2025.11365106
摘要
Accurate skin lesion segmentation is crucial for early melanoma detection and reliable medical diagnosis. Recently, such generative diffusion-based segmentation models have achieved state-of-the-art performance in this task. However, their large number of parameters hinders the deployment in real-world clinical and mobile settings. A key challenge is how to compress these models while preserving their reliability in diagnosis. To this end, we propose an edge-focused knowledge distillation (EFKD) strategy for the generative diffusion-based skin lesion segmentation, prioritizing contour information transfer from teacher to student. Accordingly, we introduce LiteDermoSegDiff, a lightweight diffusion-based lesion segmentation model that integrates knowledge distillation with boundary-aware supervision. This design ensures that the student network maintains sharp lesion boundaries while significantly reducing model parameters. Extensive experiments on the common ISIC2018 and HAM10000 dermoscopic benchmarks demonstrate that our method achieves up to 88.9% parameter reduction while maintaining competitive segmentation accuracy. These results show that diffusion-based segmentation models can be substantially compressed without compromising boundary awareness, paving the way for efficient and clinically deployable solutions in resource-constrained environments. Code can be found at https://github.com/hoangdv05/EFKD.
科研通智能强力驱动
Strongly Powered by AbleSci AI