Overcoming Data Scarcity in Scanning Tunnelling Microscopy Image Segmentation
This work addresses the burden of manual annotation for researchers in materials science and surface physics, offering a more flexible and efficient method for STM image segmentation, though it is incremental in combining existing learning techniques.
The paper tackles the problem of labor-intensive manual segmentation in scanning tunnelling microscopy (STM) image analysis by proposing an automated approach using few-shot and unsupervised learning, achieving high accuracy and adaptability to unseen surfaces with as few as one additional labeled data point.
Scanning tunnelling microscopy (STM) is a powerful technique for imaging surfaces with atomic resolution, providing insight into physical and chemical processes at the level of single atoms and molecules. A regular task of STM image analysis is the identification and labelling of features of interest against a uniform background. Performing this manually is a labour-intensive task, requiring significant human effort. To reduce this burden, we propose an automated approach to the segmentation of STM images that uses both few-shot learning and unsupervised learning. Our technique offers greater flexibility compared to previous supervised methods; it removes the requirement for large manually annotated datasets and is thus easier to adapt to an unseen surface while still maintaining a high accuracy. We demonstrate the effectiveness of our approach by using it to recognise atomic features on three distinct surfaces: Si(001), Ge(001), and TiO$_2$(110), including adsorbed AsH$_3$ molecules on the silicon and germanium surfaces. Our model exhibits strong generalisation capabilities, and following initial training, can be adapted to unseen surfaces with as few as one additional labelled data point. This work is a significant step towards efficient and material-agnostic, automatic segmentation of STM images.