PulseAugur
中
实时 08:57:43
English(EN) A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD

研究人员开发用于图像分类和分割的新型无监督域自适应框架

作者 PulseAugur 编辑部 · [6 个来源] ·

研究人员开发了新的无监督域自适应（UDA）框架，以应对将在一个数据集上训练的AI模型应用于不同、未标记数据集的挑战。一种方法利用了两个基础模型，特别是Segment Anything Model (SAM) 和 DINOv3，通过从更广泛的目标像素中学习并构建稳定、域不变的原型来改进语义分割。另一个框架专注于医学成像，采用面向方向的自适应技术对多模态MRI的脑肿瘤进行分类，并使用RKHS-MMD对X射线胸片分类进行鲁棒自适应，从而减少对大量手动标注的依赖。 AI

影响 这些UDA的进步可以显著减少AI模型开发中对大量手动数据标注的需求，从而加速在自动驾驶和医学诊断等领域的部署。

排序理由 多篇arXiv论文提出了用于计算机视觉和医学成像的无监督域自适应技术的新研究。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

研究人员开发用于图像分类和分割的新型无监督域自适应框架

报道来源 [6]

  1. arXiv cs.CV TIER_1 English(EN) · Yerin Cheon, Aruna Balasubramanian, Francois Rameau ·

    Dual-Foundation Models for Unsupervised Domain Adaptation

    arXiv:2605.03365v1 Announce Type: new Abstract: Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world data…

  2. arXiv cs.CV TIER_1 English(EN) · Sapna Sachan, Amulya Kumar Mahto, Prashant Wagambar Patil ·

    Orientation-Aware Unsupervised Domain Adaptation for Brain Tumor Classification Across Multi-Modal MRI

    arXiv:2605.03490v1 Announce Type: new Abstract: The clinical integration of deep learning models for brain tumor diagnosis in neuro-oncology is severely constrained by limited expert-annotated MRI data and substantial inter-institutional domain shift arising from variations in sc…

  3. arXiv cs.CV TIER_1 English(EN) · Sapna Sachan, Rakesh Kumar Sanodiya, Amulya Kumar Mahto ·

    A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD

    arXiv:2605.03787v1 Announce Type: new Abstract: Labeling medical images is a major bottleneck in the field of medical imaging, as it requires domain-specific expertise, and it gets further complicated due to variability across different medical centers and different imaging devic…

  4. arXiv cs.CV TIER_1 English(EN) · Amulya Kumar Mahto ·

    A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD

    Labeling medical images is a major bottleneck in the field of medical imaging, as it requires domain-specific expertise, and it gets further complicated due to variability across different medical centers and different imaging devices. Such heterogeneity introduces domain shifts …

  5. arXiv cs.CV TIER_1 English(EN) · Prashant Wagambar Patil ·

    Orientation-Aware Unsupervised Domain Adaptation for Brain Tumor Classification Across Multi-Modal MRI

    The clinical integration of deep learning models for brain tumor diagnosis in neuro-oncology is severely constrained by limited expert-annotated MRI data and substantial inter-institutional domain shift arising from variations in scanners, imaging protocols, and contrast settings…

  6. arXiv cs.CV TIER_1 English(EN) · Francois Rameau ·

    Dual-Foundation Models for Unsupervised Domain Adaptation

    Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets. Unsupervised Domain Adaptation (UDA) addre…

相关实体

相关话题