Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring

TL;DR

This paper demonstrates that combining self-supervised and few-shot learning techniques enables effective classification of bioaerosol particles from holographic images with minimal labeled data, enhancing real-time monitoring adaptability.

Contribution

It introduces a novel approach that integrates self-supervised and few-shot learning for bioaerosol classification, reducing the need for extensive labeled datasets and improving model adaptability.

Findings

Self-supervised learning improves identification accuracy with abundant unlabeled data.

Few-shot classification performance is significantly enhanced with limited labeled examples.

Workflow optimization for real-time bioaerosol monitoring is achieved.

Abstract

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep-learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and require considerable effort to produce large amounts of annotated data, an effort that must be repeated for new particles, geographical regions, or measurement systems. In this work, we show that self-supervised learning and few-shot learning can be combined to classify holographic images of bioaerosol particles using a large collection of unlabelled data and only a few examples for each particle type. We first demonstrate that self-supervision on pictures of unidentified particles from ambient air measurements enhances identification even when labelled data is abundant. Most importantly, it greatly improves few-shot classification when only a handful of labelled images are available. Our findings suggest that real-time bioaerosol monitoring workflows can be substantially optimized, and the effort required to adapt models for different situations considerably reduced.