Image-to-Image Translation with GAN for Synthetic Data Augmentation in Plant Disease Datasets

• 발행기관: 한국스마트미디어학회
• 저자명: Haseeb Nazki Jaehwan Lee Sook Yoon Dong Sun Park
• 간행물 정보: 『스마트미디어저널』Vol8, No.2, 39~51쪽, 전체 13쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2019.05.30

영문 초록

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data is an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

목차

INTRODUCTION

RELATED WORK

METHOD

EXPERIMENTS AND RESULTS

키워드

Deep Learning Image Synthesis Image-to-Image Translation Data Augmentation Data Balancing Generative Adversarial Network