Dual-Graph Knowledge Distillation for Few-Shot Class-Incremental Microorganism Recognition

SiHang Xu¹Yangfan Hu²Yinuo Zhang³Liwen Chen⁴Yimin Yin^5*

• ¹School of Computer, Hunan First Normal University, Changsha, China
• ²National University of Defense Technology School of Meteorology and Oceanology, Changsha, China
• ³PLA Rocket Force University of Engineering, Xi'An, China
• ⁴School of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, China
• ⁵School of Mathematics and Statistics, Hunan First Normal University, Changsha, China

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.