Search papers, labs, and topics across Lattice.
This paper introduces TACoS, a novel weakly supervised learning framework designed for the precise pixel-level segmentation of two-dimensional materials using minimal annotations. By integrating semi-supervised consistency learning with structured tree energy constraints, TACoS effectively aligns predictions across different views and generates structure-aware pseudo labels, significantly enhancing segmentation performance. Experiments on graphene and MoS2 datasets reveal that TACoS achieves over 96% of the performance of fully supervised methods while utilizing less than 0.6% of annotated data, showcasing its efficiency and scalability for high-throughput screening applications.
Achieving over 96% of fully supervised segmentation performance with less than 0.6% of annotated data could revolutionize the efficiency of material screening in research.
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.
