Overcoming Labelled Data Scarcity for Defect Classification in Scanning Tunneling Microscopy
arXiv:2506.01678v2 Announce Type: replace-cross Abstract: 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 learnin
The increasing availability of robust few-shot learning techniques in AI is enabling their application to traditionally labor-intensive scientific image analysis tasks.
Automating defect classification in STM images significantly streamlines materials science research and development, accelerating the discovery and optimization of new materials.
The reliance on manual human effort for interpreting complex scientific imaging data is reduced, potentially speeding up experimental cycles and data-driven material design.
- · Materials science researchers
- · Semiconductor industry
- · AI/ML developers in scientific domains
- · Advanced manufacturing
- · Manual image analysis services
Automated STM image analysis accelerates the characterization of material defects and surface properties.
Faster characterization leads to quicker development cycles for novel materials with specific desired properties.
The enhanced pace of materials discovery could underpin breakthroughs in various industries, from electronics to energy storage.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI