用合成数据训练的模型，能用少量图像精准识别低对比度二维材料
MaskTerial: A Foundation Model for Automated 2D Material Flake Detection
- 基于实例分割网络，通过合成数据预训练提升泛化能力
- 仅需5~10张图即可适配新材料，对六方氮化硼等低对比材料检测效果显著
- 结合不确定性估计实现光学对比度驱动的分类，适合材料科研人员
利用计算机视觉算法可自动检测与分类光学显微镜图像中的剥离二维（2D）材料薄片，有望提升分类准确性、客观性及样品制备效率，并支持大规模数据收集。现有算法在识别低对比度材料时表现不佳，且通常需要大量标注数据。本文提出一种深度学习模型 MaskTerial，采用实例分割网络可靠识别 2D 材料薄片。该模型通过一个无标签数据生成的合成数据生成器进行广泛预训练，生成逼真的显微图像。这使得模型仅需 5 至 10 张图像即可快速适应新材料。此外，引入不确定性估计模型，基于光学对比度对预测结果进行最终分类。我们在包含五种不同 2D 材料的八个数据集上评估该方法，结果表明在检测如六方氮化硼等低对比度材料方面显著优于现有技术。
原文摘要 · Abstract (English)
The detection and classification of exfoliated two-dimensional (2D) material flakes from optical microscope images can be automated using computer vision algorithms. This has the potential to increase the accuracy and objectivity of classification and the efficiency of sample fabrication, and it allows for large-scale data collection. Existing algorithms often exhibit challenges in identifying low-contrast materials and typically require large amounts of training data. Here, we present a deep learning model, called MaskTerial, that uses an instance segmentation network to reliably identify 2D material flakes. The model is extensively pre-trained using a synthetic data generator, that generates realistic microscopy images from unlabeled data. This results in a model that can to quickly adapt to new materials with as little as 5 to 10 images. Furthermore, an uncertainty estimation model is used to finally classify the predictions based on optical contrast. We evaluate our method on eight different datasets comprising five different 2D materials and demonstrate significant improvements over existing techniques in the detection of low-contrast materials such as hexagonal boron nitride.
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。