Transformer-based Detection of Microorganisms on High-Resolution Petri Dish Images

TL;DR

This paper presents AttnPAFPN, a transformer-based detection pipeline that improves microorganism detection in Petri dish images, achieving superior accuracy and adaptability across multiple datasets.

Contribution

Introduction of AttnPAFPN, a novel transformer variation with efficient-global self-attention for high-resolution microorganism detection in Petri dishes.

Findings

Outperforms current state-of-the-art on AGAR dataset

Effective on COCO and LIVECell datasets

Easily integrated into existing detection pipelines

Abstract

Many medical or pharmaceutical processes have strict guidelines regarding continuous hygiene monitoring. This often involves the labor-intensive task of manually counting microorganisms in Petri dishes by trained personnel. Automation attempts often struggle due to major challenges: significant scaling differences, low separation, low contrast, etc. To address these challenges, we introduce AttnPAFPN, a high-resolution detection pipeline that leverages a novel transformer variation, the efficient-global self-attention mechanism. Our streamlined approach can be easily integrated in almost any multi-scale object detection pipeline. In a comprehensive evaluation on the publicly available AGAR dataset, we demonstrate the superior accuracy of our network over the current state-of-the-art. In order to demonstrate the task-independent performance of our approach, we perform further experiments on COCO and LIVECell datasets.