English(EN) Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy

新方法通过稀疏标签和偏好改进电子显微镜分割

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-04 04:00

研究人员开发了用于电子显微镜图像域自适应分割的新方法，这对于生物学和神经科学研究至关重要。第一种方法，实例感知伪标签和类别聚焦对比学习，使用稀疏点标签和多任务学习框架来提高分割精度。第二种方法，Prefer-DAS，引入了稀疏可提示学习和局部偏好对齐，实现了交互式分割，并且优于现有的无监督和弱监督技术。 AI

影响这些在标注效率方面的分割进展可以通过减少大量手动标注的需求来加速生物学和神经科学研究。

排序理由两篇新的arXiv论文提出了用于电子显微镜域自适应分割的新颖方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Shan Xiong, Jiabao Chen, Ye Wang, Jialin Peng · 2026-05-04 04:00

Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy

arXiv:2510.16450v2 Announce Type: replace Abstract: Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) met…
arXiv cs.CV TIER_1 English(EN) · Jiabao Chen, Shan Xiong, Jialin Peng · 2026-05-04 04:00

Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

arXiv:2602.19423v3 Announce Type: replace Abstract: Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the preval…

报道来源 [2]

Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy

Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

相关实体

相关话题