发表机构
AnnLab, Institute of Semiconductors, Chinese Academy of Sciences; Institute of Semiconductors, Chinese Academy of Sciences; Center of Materials Science and Optoelectronics Engineering & School of Integrated Circuits, University of Chinese Academy of Sciences（中国科学院半导体研究所安实验室; 中国科学院半导体研究所; 中国科学院大学材料科学与光电技术中心及集成电路学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究二维材料薄片像素级定位问题，提出TACoS框架，整合半监督一致性学习与结构化树能量约束，引入不对称区域对比学习，用少量注释数据实现高性能，在复杂场景中表现优越，为二维材料高通量筛选提供高效方案。
AI 中文摘要
二维材料薄片的精确像素级定位对高通量筛选至关重要。传统全监督方法依赖密集注释，成本高且耗时，限制了分割模型实际应用。本文提出TACoS，专为二维材料设计的涂鸦分割框架。设计统一框架整合半监督一致性学习与结构化树能量约束，含无标签弱强分布对齐模块和树能量正则化模块。还引入不对称区域对比学习，融合弱增强分支高置信度预测与涂鸦形成增强标签，在表示层面增强类内凝聚和类间分离。实验表明TACoS用不到0.6%注释数据实现超96%全监督性能，在弱对比边缘和复杂背景场景中结构连贯性和边界稳定性优越，为二维材料薄片自动高通量筛选提供高效可扩展方案。
英文摘要
The precise pixel-level localization of 2D material flakes is crucial for high-throughput screening. However, traditional fully supervised methods rely on dense annotations, which are costly and time-consuming, severely limiting the practical deployment of segmentation models. This paper proposes TACoS, a specialized scribble segmentation framework tailored for 2D materials. First, we design a unified framework that integrates semi-supervised consistency learning with structured tree energy constraints. This framework comprises two core components: an unlabeled weak-strong distribution alignment module and a tree energy regularization module. The former employs cosine consistency constraints to enhance prediction alignment across views. Meanwhile, the latter utilizes minimum spanning trees to establish pixel affinity relationships and generate structure-aware soft pseudo labels for online semantic guidance. Next, we introduce asymmetric regional contrast learning. This approach fuses high-confidence predictions from the weak augmentation branch with scribbles to form augmented labels, and construct category prototypes in the representation space. Simultaneously, we prioritize contrastive constraints on challenging pixels in boundary-unlabeled regions. This strategy enhances intra-class cohesion and inter-class separation at the representation level, effectively reducing category confusion in low-contrast edges and complex backgrounds. Experiments conducted on the constructed graphene and MoS2 datasets demonstrate that our method TACoS achieves over 96% of fully supervised performance using less than 0.6% annotated data. Furthermore, it exhibits superior structural coherence and boundary stability in scenarios with weakly contrasting edges and complex backgrounds, providing an efficient and scalable solution for automated high-throughput screening of 2D material flakes.
Comments35 pages, 7 figures
