Utilizing active learning to accelerate segmentation of microstructures with tiny annotation budgets - Université Grenoble Alpes
Article Dans Une Revue Energy Storage Materials Année : 2024

Utilizing active learning to accelerate segmentation of microstructures with tiny annotation budgets

Résumé

Non-destructive 3D imaging techniques, such as X-ray nano-holo-tomography, enable the visualization of battery electrodes. Segmenting electrodes into distinct phases is crucial for a comprehensive analysis, yet the process of precise annotation is very labor-intensive. To address this challenge, deep learning methods have been leveraged for automation. However, acquiring a sufficiently large dataset for training deep neural networks that are widely usable remains impractical. A model that is applicable within a dataset but requires very limited human effort to build and use is a viable direction. We propose an active learning framework operating in a semi-supervised setting that minimizes the annotations required by identifying informative training samples at the pixel level. Our approach achieves accuracy comparable to models trained on complete datasets, while utilizing a mere 4% of the data. We demonstrate the effectiveness of our method through a quantitative analysis involving lithium nickel oxide (LNO) electrodes and a user study focusing on graphite electrodes. Our results underscore the potential of active learning to streamline data analysis through efficient model training.

Dates et versions

hal-04798608 , version 1 (22-11-2024)

Identifiants

Citer

Laura Hannemose Rieger, François Cadiou, Quentin Jacquet, Victor Vanpeene, Julie Villanova, et al.. Utilizing active learning to accelerate segmentation of microstructures with tiny annotation budgets. Energy Storage Materials, 2024, 73, pp.103785. ⟨10.1016/j.ensm.2024.103785⟩. ⟨hal-04798608⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More