BioGAN: An unpaired GAN-based image to image translation model for microbiological images

TL;DR

BioGAN is a novel unpaired GAN model that translates microbiological laboratory images into field images, enhancing dataset diversity and significantly improving object detection performance in microbiology applications.

Contribution

The paper introduces BioGAN, an unpaired and unsupervised GAN model utilizing Adversarial and Perceptual loss for microbiological image translation, which was not previously explored in this context.

Findings

Generated field images improved object detection metrics by up to 68.1% F1-score.

BioGAN effectively transforms lab images into realistic field images.

The approach enhances dataset diversity for microbiological image analysis.

Abstract

A diversified dataset is crucial for training a well-generalized supervised computer vision algorithm. However, in the field of microbiology, generation and annotation of a diverse dataset including field-taken images are time consuming, costly, and in some cases impossible. Image to image translation frameworks allow us to diversify the dataset by transferring images from one domain to another. However, most existing image translation techniques require a paired dataset (original image and its corresponding image in the target domain), which poses a significant challenge in collecting such datasets. In addition, the application of these image translation frameworks in microbiology is rarely discussed. In this study, we aim to develop an unpaired GAN-based (Generative Adversarial Network) image to image translation model for microbiological images, and study how it can improve generalization ability of object detection models. In this paper, we present an unpaired and unsupervised image translation model to translate laboratory-taken microbiological images to field images, building upon the recent advances in GAN networks and Perceptual loss function. We propose a novel design for a GAN model, BioGAN, by utilizing Adversarial and Perceptual loss in order to transform high level features of laboratory-taken images into field images, while keeping their spatial features. The contribution of Adversarial and Perceptual loss in the generation of realistic field images were studied. We used the synthetic field images, generated by BioGAN, to train an object-detection framework, and compared the results with those of an object-detection framework trained with laboratory images; this resulted in up to 68.1% and 75.3% improvement on F1-score and mAP, respectively. Codes is publicly available at https://github.com/Kahroba2000/BioGAN.