Dual-graph knowledge distillation for few-shot class-incremental microorganism recognition
Frontiers in Microbiology · 09.03.2026 · 17
DOI: 10.3389/fmicb.2026.1791871 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Microbiology, online erschienen am 09.03.2026. Verfasst von Sihang Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer, Hunan First Normal University, Changsha, China. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Environmental microorganism recognition from microscopic images is crucial for environmental monitoring and ecological analysis. In practical scenarios, microorganism categories often evolve over time, and newly emerging classes usually have only a few labeled samples due to high annotation costs. This combination naturally gives rise to the few-shot class-incremental learning (FSCIL) problem. FSCIL requires models to incrementally learn new classes under severe data scarcity while effectively retaining knowledge of previously learned ones. In this work, we propose a unified FSCIL framework for environmental microorganism recognition. The proposed method is composed of three complementary components. First, a contrastive-inspired fine-grained representation learning strategy is introduced in the base session. This strategy enhances intra-class compactness by mining prediction-consistent augmented samples, without introducing explicit contrastive losses. Second, a prototype rectification mechanism is designed to stabilize the representations of incremental classes by leveraging semantic structures learned from base classes. Third, a dual-graph knowledge distillation framework is proposed to preserve both instance-level and class-level relational knowledge during incremental learning. This process is guided by a teacher model updated via exponential moving average. Experiments conducted on the EMDS-7 dataset demonstrate the effectiveness of the proposed approach. Compared with state-of-the-art FSCIL methods, our method achieves the highest average accuracy of 78.19% and maintains the best final-session accuracy of 65.36%. Meanwhile, strong base-session performance is consistently preserved. These results indicate that the proposed framework effectively mitigates catastrophic forgetting and enables robust adaptation to new microorganism categories in real-world incremental recognition scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer, Hunan First Normal University, Changsha, China.
- School of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, China.
- College of Meteorology and Oceanography, National University of Defense Technology, Changsha, China.
- Rocket Force University of Engineering, Xi'an, China.
- School of Mathematics and Statistics, Hunan First Normal University, Changsha, China.
Zitieren
APA
Xu, S., Hu, Y., Zhang, Y., Chen, L., & Yin, Y. (2026). Dual-graph knowledge distillation for few-shot class-incremental microorganism recognition. Frontiers in Microbiology, 17. https://doi.org/10.3389/fmicb.2026.1791871
Vancouver
Xu S, Hu Y, Zhang Y, Chen L, Yin Y. Dual-graph knowledge distillation for few-shot class-incremental microorganism recognition. Frontiers in Microbiology. 2026;17. doi:10.3389/fmicb.2026.1791871
BibTeX
@article{Xu2026,
author = {Xu, Sihang and Hu, Yangfan and Zhang, Yinuo and Chen, Liwen and Yin, Yimin},
title = {Dual-graph knowledge distillation for few-shot class-incremental microorganism recognition},
journal = {Frontiers in Microbiology},
year = {2026},
volume = {17},
doi = {10.3389/fmicb.2026.1791871}
}
EUVIMED