Unsupervised Image Translation using Adversarial Networks for Improved Plant Disease Recognition

TL;DR

This paper introduces AR-GAN, an enhanced unsupervised image translation method using GANs to generate high-quality synthetic images, which improves plant disease recognition accuracy by addressing data imbalance issues.

Contribution

The paper presents AR-GAN, a novel GAN-based image translation model that enhances image quality and semantics for plant disease datasets, improving classification performance.

Findings

Synthetic images improved classification accuracy by 5.2%.

AR-GAN outperforms existing models in image quality and semantic preservation.

Synthetic data augmentation surpasses classical methods in imbalanced datasets.

Abstract

Acquisition of data in task-specific applications of machine learning like plant disease recognition is a costly endeavor owing to the requirements of professional human diligence and time constraints. In this paper, we present a simple pipeline that uses GANs in an unsupervised image translation environment to improve learning with respect to the data distribution in a plant disease dataset, reducing the partiality introduced by acute class imbalance and hence shifting the classification decision boundary towards better performance. The empirical analysis of our method is demonstrated on a limited dataset of 2789 tomato plant disease images, highly corrupted with an imbalance in the 9 disease categories. First, we extend the state of the art for the GAN-based image-to-image translation method by enhancing the perceptual quality of the generated images and preserving the semantics. We introduce AR-GAN, where in addition to the adversarial loss, our synthetic image generator optimizes on Activation Reconstruction loss (ARL) function that optimizes feature activations against the natural image. We present visually more compelling synthetic images in comparison to most prominent existing models and evaluate the performance of our GAN framework in terms of various datasets and metrics. Second, we evaluate the performance of a baseline convolutional neural network classifier for improved recognition using the resulting synthetic samples to augment our training set and compare it with the classical data augmentation scheme. We observe a significant improvement in classification accuracy (+5.2%) using generated synthetic samples as compared to (+0.8%) increase using classic augmentation in an equal class distribution environment.