Enhancing Shrimp Disease Detection via Deep Learning and Data Refinement for Resilient Aquaculture
cs.CV, cs.AI, cs.ET
Submitted: 2026-09-20
Updated: 2026-09-20
Comments: This paper has been accepted at the International Conference on Multidisciplinary Research (ICMR 2025)
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Shrimp diseases continue to cause devastating losses in the aquaculture industry, driving a critical need for robust, automated detection.
Terminology
Abstract
Shrimp diseases continue to cause devastating losses in the aquaculture industry, driving a critical need for robust, automated detection. This work contributes the first application of Vision Transformers (ViT) and Self-Supervised Learning (SSL) to the shrimp farming domain, addressing both performance bottlenecks and data labeling challenges. We propose two deep learning pipelines to classify four key diseases: Healthy, Black Gill (BG), White Spot Syndrome Virus (WSSV), and a co-infection of both using a dataset of 4,348 images. First, our supervised transfer-learning approach leverages ImageNet-pretrained ViT-Small/16 and EfficientNet backbones. Second, we introduce a contrastive learning framework (SimCLR) with a ViT-Small encoder to extract robust representations from unlabeled images prior to fine-tuning. Our results establish strong new baselines for sustainable aquaculture monitoring. The supervised approach achieves an outstanding 96% accuracy with fast convergence, outperforming traditional generic models, while the label-efficient SSL approach reaches a highly competitive 85% validation accuracy.
Sources
- Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
- An Introduction to Convolutional Neural Networks
- Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
- A comparative study between vision transformers and CNNs in digital pathology
- A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
- Contrastive Learning for Label-Efficient Semantic Segmentation
- Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout
- Densely Connected Convolutional Networks
- Going Deeper with Convolutions
- You Only Look Once: Unified, Real-Time Object Detection
- Decoupled Weight Decay Regularization
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
- DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning
- G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling
- Attention Is All You Need
- InfoNCE: Identifying the Gap Between Theory and Practice
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models