PulseAugur
LIVE 13:03:53
research · [2 sources] ·
0
research

New methods improve electron microscopy segmentation with sparse labels and preferences

Researchers have developed new methods for domain adaptive segmentation of electron microscopy images, crucial for biological and neuroscience research. The first approach, Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning, uses sparse point labels and a multitask learning framework to improve segmentation accuracy. The second method, Prefer-DAS, introduces sparse promptable learning and local preference alignment, allowing for interactive segmentation and outperforming existing unsupervised and weakly-supervised techniques. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT These advancements in annotation-efficient segmentation could accelerate biological and neuroscience research by reducing the need for extensive manual labeling.

RANK_REASON Two new arXiv papers present novel methods for domain adaptive segmentation in electron microscopy.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Shan Xiong, Jiabao Chen, Ye Wang, Jialin Peng ·

    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…

  2. arXiv cs.CV TIER_1 · Jiabao Chen, Shan Xiong, Jialin Peng ·

    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…