Efficient deep learning architectures for fast identification of bacterial strains in resource-constrained devices

This work presents twelve fine-tuned deep learning architectures to solve the bacterial classification problem over the digital image of bacterial species dataset. The base architectures were mainly published as mobile or efficient solutions to the ImageNet challenge, and all experiments presented in this work consisted in making several modifications to the original designs, in order to make them able to solve the bacterial classification problem by using fine-tuning and transfer learning techniques. This work also proposes a novel data augmentation technique for this dataset, which is based on the idea of artificial zooming, strongly increasing the performance of every tested architecture, even doubling it in some cases. In order to get robust and complete evaluations, all experiments were performed with 10-fold cross-validation and evaluated with five different metrics: top-1 and top-5 accuracy, precision, recall, and F1 score. This paper presents a complete comparison of the twelve different architectures, cross-validated with the original and the augmented version of the dataset, the results are also compared with several literature methods. Overall, eight of the eleven architectures surpassed the 0.95 score in top-1 accuracy with our data augmentation method, being 0.9738 the highest top-1 accuracy. The impact of the data augmentation technique is reported with relative improvement scores.