Scholarlink

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. As shown in our previous work [1] contrastive pre-training has strong potential on medical images. However, further research is necessary to incorporate the particular characteristics of these images.We hypothesize that the similarity of medical images hinders the success of contrastive learning in the medical imaging domain.

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

Abstract: Selective Reduction of CT Data for Self-supervised Pre-training Improves Downstream Classification Performance

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Daniel Wolf,
  • Tristan Payer,
  • Catharina S. Lisson,
  • Christoph G. Lisson,
  • Meinrad Beer,
  • Michael Götz,
  • Timo Ropinski

摘要

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. As shown in our previous work [1] contrastive pre-training has strong potential on medical images. However, further research is necessary to incorporate the particular characteristics of these images.We hypothesize that the similarity of medical images hinders the success of contrastive learning in the medical imaging domain.