Exemplar：经典先验补充冻结特征用于原生分辨率的少样本显微镜图像分割
Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolution
浏览论文内容
中文总结 AI 辅助
Exemplar是一种融合冻结DINOv3骨干与经典滤波器响应库的少样本显微镜图像分割方法，在11个生物医学数据集上性能优于多数少样本方法，仅单个标注掩码时也优于从头训练的nnU-Net，拟合速度远快于nnU-Net。
中文摘要 AI 辅助
分割新的生物医学数据集通常需要在大量标注数据上训练的特定领域模型，或在推理时引导的基础模型。我们提出Exemplar，一种少样本分割器，它将冻结的DINOv3骨干网络与固定的经典原生分辨率滤波器响应库融合在一个轻量级头部中，该头部仅从支持掩码拟合。在少掩码、原生分辨率的场景下，经典先验和冻结的自监督特征具有互补性：融合在一个头部中，单一固定配置可覆盖11个生物医学成像数据集。在同一头部下，仅经典库在11个数据集面板上的前景交并比或中心线Dice得分为0.693，仅冻结特征得分为0.672；库在11个数据集中的7个上表现更好，特征在其余4个上表现更好，融合后得分达0.782。与5种前向传播少样本方法相比，Exemplar在55种方法-数据集对比中的54种中领先，其中52种在Holm校正后具有统计学意义。从单个标注掩码出发，它在同一面板上的得分为0.703，而基于该相同掩码从头训练的nnU-Net得分为0.682。在8个掩码时，nnU-Net在面板均值上超过它，主要在中心线一致性方面，但拟合时间是Exemplar的16至77倍。
英文摘要
Segmenting a new biomedical dataset usually means a domain-specific model trained on substantial annotation, or a foundation model steered at inference time. We present Exemplar, a few-shot segmenter that fuses a frozen DINOv3 backbone with a fixed bank of classical native-resolution filter responses in one lightweight head, fitted from the support masks alone. In the few-mask, native-resolution regime, classical priors and frozen self-supervised features are complementary: fused in one head, a single fixed configuration spans eleven biomedical imaging datasets. Under the same head, the classical bank alone reaches 0.693 on the eleven-dataset panel, scored by foreground intersection-over-union or centreline Dice, and the frozen features alone 0.672; the bank leads on seven of the eleven and the features on the rest, and fused they reach 0.782. Against five forward-pass few-shot methods, Exemplar leads in 54 of 55 method-dataset comparisons, 52 of them significant after Holm correction. From a single annotated mask it reaches 0.703 on the same panel, against 0.682 for a from-scratch nnU-Net trained on that same mask. At eight masks nnU-Net overtakes it on the panel mean, chiefly on centreline agreement, but takes 16-77x longer to fit.
发表机构
- The Czech Academy of Sciences（捷克科学院）
- Czech Technical University in Prague（布拉格捷克技术大学）
机构由 AI 辅助整理，请以论文原文为准。
