Abstract:

Fine-scale pixel-level annotation of minirhizotron root images is a less common and challenging task. We present an interactive segmentation framework to accelerate root annotation. We leverage the concept of few-shot segmentation so that the pre-trained model can be effectively fine-tuned and transferred to an unseen category. To provide immediate feedback for real-time interaction, we adapted a UNet architecture by attaching lightweight embedding layers which leveraged a prototype learning approach to efficiently learn the data metric in the embedding space. The prototypes optimized by the prototype loss preserve the within-class data variation, enabling effective fine-tuning. Furthermore, we designed a system with our interactive annotation framework, and conducted an experiment with real users to validate the approach.

Links:

Citation:

X. Guo, A. Zare, L. Anthony, and F. B. Fritschi, "Interactive segmentation with prototype learning for few-shot root annotation," IEEE Transactions on Geoscience and Remote Sensing, pp. 1–1, 2025, doi: 10.1109/TGRS.2025.3556799.

@article{guo2025interactive,
title={Interactive Segmentation with Prototype Learning for Few-Shot Root Annotation},
author={Guo, Xiaolei and Zare, Alina and Anthony, Lisa and Fritschi, Felix B},
journal={IEEE Transactions on Geoscience and Remote Sensing},
year={2025},
publisher={IEEE}
}