ShrimpXNet: A Transfer Learning Framework for Shrimp Disease Classification with Augmented Regularization, Adversarial Training, and Explainable AI

TL;DR

This paper introduces ShrimpXNet, a transfer learning framework utilizing advanced augmentation, adversarial training, and explainability techniques to accurately classify shrimp diseases with high performance and robustness.

Contribution

It presents a novel deep learning framework combining transfer learning, adversarial training, and explainable AI for shrimp disease classification, achieving state-of-the-art accuracy.

Findings

ConvNeXt-Tiny achieved 96.88% accuracy.

Adversarial training improved model robustness.

Explainability methods visualized model attention regions.

Abstract

Shrimp is one of the most widely consumed aquatic species globally, valued for both its nutritional content and economic importance. Shrimp farming represents a significant source of income in many regions; however, like other forms of aquaculture, it is severely impacted by disease outbreaks. These diseases pose a major challenge to sustainable shrimp production. To address this issue, automated disease classification methods can offer timely and accurate detection. This research proposes a deep learning-based approach for the automated classification of shrimp diseases. A dataset comprising 1,149 images across four disease classes was utilized. Six pretrained deep learning models, ResNet50, EfficientNet, DenseNet201, MobileNet, ConvNeXt-Tiny, and Xception were deployed and evaluated for performance. The images background was removed, followed by standardized preprocessing through the Keras image pipeline. Fast Gradient Sign Method (FGSM) was used for enhancing the model robustness through adversarial training. While advanced augmentation strategies, including CutMix and MixUp, were implemented to mitigate overfitting and improve generalization. To support interpretability, and to visualize regions of model attention, post-hoc explanation methods such as Grad-CAM, Grad-CAM++, and XGrad-CAM were applied. Exploratory results demonstrated that ConvNeXt-Tiny achieved the highest performance, attaining a 96.88% accuracy on the test dataset. After 1000 iterations, the 99% confidence interval for the model is [0.953,0.971].