发表机构
Institute for Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich GmbH（于利希研究中心材料数据科学与信息学研究所（IAS-9））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对科学成像的物理测量特性，提出了一套物理对齐的自监督学习增强设计流程，在五种SSL范式的分类和回归任务中显著提升了下游性能。
AI 中文摘要
数据增强定义了自监督学习（SSL）所学习的不变性。标准增强流程是为自然图像设计的，但科学成像模态受具有独特对称性和采集约束的物理测量过程支配。强制实施与这些约束矛盾的不变性会扭曲学习到的表示并限制下游性能，而从机器学习转向新科学模态的从业者目前除了不加检验地迁移自然图像流程外几乎没有指导。我们通过一种原则性、可复现的科学SSL增强设计流程来解决这一差距：我们将物理对齐的增强集形式化为测量一致对称性与采集驱动扰动的结合，并提供了一个具体的、主要无标签的工作流程——枚举候选、按测量算子标记每个候选、用表示几何诊断验证、并通过单因素消融确认——以选择这些增强。我们针对实空间电子显微镜和倒易空间4D-STEM衍射实例化该流程，并在五个SSL范式（DINOv2、SimCLR、MAE、VICRegL、I-JEPA）上针对分类和晶体取向回归进行评估。物理对齐的增强显著提升了依赖跨视图一致性的目标的下游性能，降低了测地线误差并提升了在真实采集变异性（探测器增益、分辨率损失）下的鲁棒性，且系统性地重塑了表示几何。尽管我们的实验使用了电子显微镜，但该流程与模态无关，适用于其他测量驱动领域，如医学和遥感成像。这些结果将增强设计定位为科学自监督学习中主要且可控的归纳偏差来源。
英文摘要
Data augmentations define the invariances learned by self-supervised learning (SSL). Standard augmentation pipelines were designed for natural images, yet scientific imaging modalities are governed by physical measurement processes with distinct symmetry and acquisition constraints. Enforcing invariances that contradict these constraints can distort learned representations and limit downstream performance, but practitioners moving from machine learning into a new scientific modality currently have little guidance beyond transferring natural-image pipelines unexamined. We address this gap with a principled, reproducible procedure for augmentation design in scientific SSL: we formalise the physics-aligned augmentation set as a union of measurement-consistent symmetries and acquisition-driven perturbations, and we give a concrete, largely label-free workflow---enumerate candidates, label each by the measurement operator, validate with representation-geometry diagnostics, and confirm by single-factor ablation---for selecting them. We instantiate the procedure for real-space electron microscopy and reciprocal-space 4D-STEM diffraction, and evaluate it across five SSL paradigms (DINOv2, SimCLR, MAE, VICRegL, I-JEPA) on classification and crystal-orientation regression. Physics-aligned augmentations substantially improve downstream performance for objectives relying on cross-view consistency, reduce geodesic error and improve robustness under realistic acquisition variability (detector gain, resolution loss), and systematically reshape representation geometry. While our experiments use electron microscopy, the procedure is modality-agnostic and applies to other measurement-driven domains such as medical and remote-sensing imaging. These results position augmentation design as a primary, and controllable, source of inductive bias in scientific self-supervised learning.
