🤖 AI Summary
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.
📝 Abstract
This paper considers open-set recognition (OSR) of plankton images. Plankton include a diverse range of microscopic aquatic organisms that have an important role in marine ecosystems as primary producers and as a base of food webs. Given their sensitivity to environmental changes, fluctuations in plankton populations offer valuable information about oceans' health and climate change motivating their monitoring. Modern automatic plankton imaging devices enable the collection of large-scale plankton image datasets, facilitating species-level analysis. Plankton species recognition can be seen as an image classification task and is typically solved using deep learning-based image recognition models. However, data collection in real aquatic environments results in imaging devices capturing a variety of non-plankton particles and plankton species not present in the training set. This creates a challenging fine-grained OSR problem, characterized by subtle differences between taxonomically close plankton species. We address this challenge by conducting extensive experiments on three OSR approaches using both phyto- and zooplankton images analyzing also on the effect of the rejection thresholds for OSR. The results demonstrate that high OSR accuracy can be obtained promoting the use of these methods in operational plankton research. We have made the data publicly available to the research community.