用图像分布差异选最优预训练模型，提升神经元分割效率
NeuroADDA: Active Discriminative Domain Adaptation in Connectomic
- 基于图像分布差异选择最佳源域，指导迁移学习
- 仅需4个样本即降低25%-67%分割误差（变差信息）
- 发现物种间特征距离与进化关系相关，具生物学意义
从零训练分割模型是电子显微镜连接组学新数据集的常规做法。但利用已有数据集的预训练模型可在标注预算有限时提升效率与性能。本研究分析了涵盖不同生物的六个主要数据集，发现神经元图像分布间的最大均值差异（MMD）可有效预测迁移能力，并确定最优源域。基于此，提出NeuroADDA方法，结合最优域选择与无源主动学习，高效适配预训练主干网络至新数据集。在多种数据集和微调样本量下，NeuroADDA均优于从零训练，尤其在n=4时，变差信息降低25%-67%。进一步发现，多物种神经元图像在特征空间中的分布距离与系统发育距离显著相关。
原文摘要 · Abstract (English)
Training segmentation models from scratch has been the standard approach for new electron microscopy connectomics datasets. However, leveraging pretrained models from existing datasets could improve efficiency and performance in constrained annotation budget. In this study, we investigate domain adaptation in connectomics by analyzing six major datasets spanning different organisms. We show that, Maximum Mean Discrepancy (MMD) between neuron image distributions serves as a reliable indicator of transferability, and identifies the optimal source domain for transfer learning. Building on this, we introduce NeuroADDA, a method that combines optimal domain selection with source-free active learning to effectively adapt pretrained backbones to a new dataset. NeuroADDA consistently outperforms training from scratch across diverse datasets and fine-tuning sample sizes, with the largest gain observed at $n=4$ samples with a 25-67\% reduction in Variation of Information. Finally, we show that our analysis of distributional differences among neuron images from multiple species in a learned feature space reveals that these domain "distances" correlate with phylogenetic distance among those species.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。