Scholarlink

<p>In this paper, we propose a method for reducing the bias in skin disease identification for people of color with the aid of lesion only zero shot unsupervised approach that is then passed to the classifier Dermnet comprising of a hybrid Vision Transformer and Convolutional Neural Network, achieving robust validation accuracy of approximately 81%. Our Segmentation without training with labeled data as is the case with traditional U-Net has achieved an IOU of 90% across all skin colors in segmenting the lesion from skin effectively eradicating the impact of skin in the classification of disease.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DermNet: integrative CNN-ViT architecture for bias mitigation in dermatological diagnostics using advanced unsupervised lesion segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月15日

查看全文
  • Muhammad Huzaifa Imran,
  • Muhammad Shahid,
  • Mohammad Aazam,
  • Rafia Sajid,
  • Muhammad Aamir Adnan,
  • Khawar Naeem,
  • Amjad Ali

摘要

In this paper, we propose a method for reducing the bias in skin disease identification for people of color with the aid of lesion only zero shot unsupervised approach that is then passed to the classifier Dermnet comprising of a hybrid Vision Transformer and Convolutional Neural Network, achieving robust validation accuracy of approximately 81%. Our Segmentation without training with labeled data as is the case with traditional U-Net has achieved an IOU of 90% across all skin colors in segmenting the lesion from skin effectively eradicating the impact of skin in the classification of disease.