Open-Set Plankton Recognition
This work addresses the challenge of open-set recognition (OSR) for plankton in real-world underwater scenarios, where fine-grained classification is severely impeded by unknown species and abiotic particle interference. We propose a robust OSR framework centered on adaptive rejection threshold tuning, systematically evaluating— for the first time—three mainstream OSR paradigms for fine-grained identification of phytoplankton and zooplankton. Our approach integrates deep learning classifiers with a threshold-driven mechanism to reject out-of-distribution samples. Evaluated on a multi-source plankton image dataset, it achieves significant OSR improvements: 12.3% reduction in false positive rate at 95% true positive rate (FPR95) and an 8.7% increase in area under the receiver operating characteristic curve (AUROC). The code and dataset are publicly released. This work delivers a deployable, reproducible, fine-grained OSR solution for intelligent marine ecological monitoring.