Leakage-Aware Cross-Dataset Multi-Task Learning for Shrimp Disease Recognition and Biomass Estimation
DOI:
https://doi.org/10.62411/jcta.17815Keywords:
Acquisition Confounding, Biomass Estimation, Data Leakage, Disease Recognition, Domain Generalization, Multi-Task Learning, Partial Labels, Shrimp AquacultureAbstract
Public shrimp image collections are reused to train disease classifiers and non-invasive biomass estimators, yet they mix originals with published augmentations, byte-identical copies, and repeated views of the same animal, potentially inflating performance through data leakage. This study examines what these collections support once leakage is controlled: how protocol and acquisition conditions, rather than architecture alone, influence performance; whether disease recognition transfers to an independently collected dataset; and whether monocular imagery supports individual-weight estimation. One encoder is trained across three public datasets under masked supervision, using a grouping strategy that accounts for duplicates, augmentations, near-duplicates, and repeated views; a 22-check audit guides training and evaluation, with 240 runs reported. Regrouping by animal rather than file eliminates the 84.8–92.6% animal overlap in ShrimpDiseaseImageBD test folds, reducing it to 0.0%. A random image-level split yields 0.976 balanced accuracy, but 63% of its test records are published augmented copies; using originals alone yields 0.947, compared with 0.934 in the augmentation-enabled group-aware arm, which tests different original records. Transfer is asymmetric: the best-performing encoder reaches 0.615 balanced accuracy and 0.751 area under the curve on TigerShrimpBD; on ShrimpDiseaseImageBD, every encoder ranks below chance, with values of 0.271–0.390. TigerShrimpBD's 0.998 within-dataset score is affected by acquisition confounding, as every recovered capture session contains only one health class. Holding out a physical site increases biomass error from 3.18 g to 9.20 g, indicating limited cross-site generalization. The contribution is a reusable audit and evaluation protocol for interpreting performance on such collections.References
M. Iftehimul, N. A. Hasan, D. Bass, A. Bashar, M. M. Haque, and M. Santi, “Combating White Spot Syndrome Virus (WSSV) in Global Shrimp Farming: Unraveling Its Biology, Pathology, and Control Strategies,” Viruses, vol. 17, no. 11, p. 1463, Oct. 2025, doi: 10.3390/v17111463.
N. Jesintha, N. Jayakumar, and K. Madhavi, “Length-weight relationship and Fulton’s condition factor of two penaeid shrimp species, Fenneropenaeus indicus and Penaeus monodon of Pulicat Lake, southeast coast of India (Decapoda, Dendrobranchiata),” Crustaceana, vol. 98, no. 3, pp. 283–293, Apr. 2025, doi: 10.1163/15685403-bja10444.
M. S. Eder, K. C. Ampolitod, N. H. Bolao, R. J. A. Pajal, and E. M. D. Racho, “SHRIMPAI: A Mobile Application for the Early Detection of White Spot Syndrome Virus in Shrimp Using Convolutional Neural Network,” Mindanao J. Sci. Technol., vol. 22, no. 2, pp. 196–220, Dec. 2024, doi: 10.61310/mjst.v22i2.2189.
S. Sharma et al., “A lightweight deep learning architecture for automatic shrimp disease classification,” Sci. Rep., vol. 16, no. 1, p. 13837, Mar. 2026, doi: 10.1038/s41598-026-44195-z.
Y. Ektefaie, A. Shen, D. Bykova, M. G. Marin, M. Zitnik, and M. Farhat, “Evaluating generalizability of artificial intelligence models for molecular datasets,” Nat. Mach. Intell., vol. 6, no. 12, pp. 1512–1524, Dec. 2024, doi: 10.1038/s42256-024-00931-6.
M. Xu, J.-E. Park, J. Lee, J. Yang, and S. Yoon, “Plant disease recognition datasets in the age of deep learning: challenges and opportunities,” Front. Plant Sci., vol. 15, p. 1452551, Sep. 2024, doi: 10.3389/fpls.2024.1452551.
B. G. Hill, F. L. Koback, and P. L. Schilling, “The risk of shortcutting in deep learning algorithms for medical imaging research,” Sci. Rep., vol. 14, no. 1, p. 29224, Nov. 2024, doi: 10.1038/s41598-024-79838-6.
L. D. Tuan, L. N. An, and D. D. Thai, “Beyond Reported Accuracy: A Verifiability-Focused, Multi-Axis Review of Content and Context Based Fake News Detection,” J. Comput. Theor. Appl., vol. 4, no. 2, pp. 475–501, Sep. 2026, doi: 10.62411/jcta.17476.
M. M. Islam et al., “ShrimpDiseaseBD: An image dataset for detecting shrimp diseases in the aquaculture sector of Bangladesh,” Data Br., vol. 60, p. 111553, Jun. 2025, doi: 10.1016/j.dib.2025.111553.
S. I. Ahmed and D. M. Farid, “TigerShrimpBD: A Tiger Shrimp Image Dataset,” 2025, Mendeley Data. doi: 10.17632/9dj4sk5d55.1.
F. J. Ramírez-Coronel, E. Esquer-Miranda, O. M. Rodríguez-Elias, P. García-Hinostro, and G. C. Parra-Salazar, “A Litopenaeus vannamei shrimp dataset for artificial intelligence-based biomass estimation and organism detection algorithms,” Data Br., vol. 57, p. 110964, Dec. 2024, doi: 10.1016/j.dib.2024.110964.
B. Büyükarıkan, “Robust shrimp disease detection using multi-model convolutional neural networks-based ensemble strategies,” Aquac. Eng., vol. 111, p. 102616, Oct. 2025, doi: 10.1016/j.aquaeng.2025.102616.
T. Aung, R. Vanichviriyakit, K. Chayantrakom, S. Amornsamankul, and P. Huabsomboon, “CNN-Based Identification of Pathogens of Concern in Shrimp,” Animals, vol. 15, no. 21, p. 3194, Nov. 2025, doi: 10.3390/ani15213194.
R. K. Rachman, D. R. I. M. Setiadi, A. Susanto, K. Nugroho, and H. M. M. Islam, “Enhanced Vision Transformer and Transfer Learning Approach to Improve Rice Disease Recognition,” J. Comput. Theor. Appl., vol. 1, no. 4, pp. 446–460, Apr. 2024, doi: 10.62411/jcta.10459.
N. Chirdchoo, S. Mukviboonchai, and W. Cheunta, “A deep learning model for estimating body weight of live pacific white shrimp in a clay pond shrimp aquaculture,” Intell. Syst. with Appl., vol. 24, p. 200434, Dec. 2024, doi: 10.1016/j.iswa.2024.200434.
N. A. Ubina, S.-C. Cheng, C.-C. Chang, S.-Y. Cai, H.-Y. Lan, and H.-Y. Lu, “Intelligent Underwater Stereo Camera Design for Fish Metric Estimation Using Reliable Object Matching,” IEEE Access, vol. 10, pp. 74605–74619, 2022, doi: 10.1109/ACCESS.2022.3185753.
A. Setiawan, H. Hadiyanto, and C. E. Widodo, “Shrimp Body Weight Estimation in Aquaculture Ponds Using Morphometric Features Based on Underwater Image Analysis and Machine Learning Approach,” Rev. d’Intelligence Artif., vol. 36, no. 6, pp. 905–912, Dec. 2022, doi: 10.18280/ria.360611.
J. Zhang, S. Zhang, X. Liu, X. Feng, Y. Liao, and T. Pan, “Monocular fish body length estimation via brightness attenuation and fish eye scale structural constraints: application in industrial recirculating aquaculture systems,” Aquac. Int., vol. 34, no. 6, p. 210, Jul. 2026, doi: 10.1007/s10499-026-02610-2.
T. Durand, N. Mehrasa, and G. Mori, “Learning a Deep ConvNet for Multi-Label Classification With Partial Labels,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA: IEEE, Jun. 2019, pp. 647–657. doi: 10.1109/CVPR.2019.00074.
A. Kendall, Y. Gal, and R. Cipolla, “Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, Jun. 2018, pp. 7482–7491. doi: 10.1109/CVPR.2018.00781.
K. Zhou, Y. Yang, Y. Qiao, and T. Xiang, “Domain Generalization with MixStyle,” in International Conference on Learning Representations (ICLR), 2021. [Online]. Available: https://openreview.net/forum?id=6xHJ37MVxxp
B. Sun and K. Saenko, “Deep CORAL: Correlation Alignment for Deep Domain Adaptation,” in Computer Vision -- ECCV 2016 Workshops, in Lecture Notes in Computer Science. , Cham, Switzerland: Springer, 2016, pp. 443–450. doi: 10.1007/978-3-319-49409-8_35.
A. Ahmad, A. El Gamal, and D. Saraswat, “Toward Generalization of Deep Learning-Based Plant Disease Identification Under Controlled and Field Conditions,” IEEE Access, vol. 11, pp. 9042–9057, 2023, doi: 10.1109/ACCESS.2023.3240100.
A. Fitzgerald, C. C. Ioannou, S. Consuegra, A. Dowsey, and C. Garcia de Leaniz, “Machine Vision Applications for Welfare Monitoring in Aquaculture: Challenges and Opportunities,” Aquac. Fish Fish., vol. 5, no. 1, p. e70036, Feb. 2025, doi: 10.1002/aff2.70036.
S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, p. 100804, Sep. 2023, doi: 10.1016/j.patter.2023.100804.
A. J. DeGrave, J. D. Janizek, and S.-I. Lee, “AI for radiographic COVID-19 detection selects shortcuts over signal,” Nat. Mach. Intell., vol. 3, no. 7, pp. 610–619, May 2021, doi: 10.1038/s42256-021-00338-7.
M. Roberts et al., “Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans,” Nat. Mach. Intell., vol. 3, no. 3, pp. 199–217, Mar. 2021, doi: 10.1038/s42256-021-00307-0.
Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA: IEEE, Jun. 2022, pp. 11966–11976. doi: 10.1109/CVPR52688.2022.01167.
A. Howard et al., “Searching for MobileNetV3,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, South Korea: IEEE, Oct. 2019, pp. 1314–1324. doi: 10.1109/ICCV.2019.00140.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in Proceedings of the 36th International Conference on Machine Learning, PMLR, vol. 97, 2019, pp. 6105–6114. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html
Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada: IEEE, Oct. 2021, pp. 9992–10002. doi: 10.1109/ICCV48922.2021.00986.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, “Focal Loss for Dense Object Detection,” in 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy: IEEE, Oct. 2017, pp. 2999–3007. doi: 10.1109/ICCV.2017.324.
T. Ridnik et al., “Asymmetric Loss For Multi-Label Classification,” in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada: IEEE, Oct. 2021, pp. 82–91. doi: 10.1109/ICCV48922.2021.00015.
M. Ilse, J. M. Tomczak, and M. Welling, “Attention-based Deep Multiple Instance Learning,” in Proceedings of the 35th International Conference on Machine Learning, PMLR, vol. 80, 2018, pp. 2127–2136. [Online]. Available: https://proceedings.mlr.press/v80/ilse18a.html
M. R. Maulana, P. Sudira, P. Priyanto, Y. A. Fadlullah, D. Nurdiana, and A. H. Bin Sofhi @ Subhi, “Explainable Machine Learning for Predicting Indonesian Vocational School Accreditation: Geographic Validation, Probability Calibration, and Subgroup Auditing,” J. Comput. Theor. Appl., vol. 4, no. 2, pp. 502–516, Sep. 2026, doi: 10.62411/jcta.17721.
I. Loshchilov and F. Hutter, “Decoupled Weight Decay Regularization,” Jan. 04, 2019. doi: 10.48550/arXiv.1711.05101.
C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On Calibration of Modern Neural Networks,” in Proceedings of the 34th International Conference on Machine Learning, PMLR, vol. 70, 2017, pp. 1321–1330. [Online]. Available: https://proceedings.mlr.press/v70/guo17a.html
S. Holm, “A Simple Sequentially Rejective Multiple Test Procedure,” Scandinavian Journal of Statistics, vol. 6, no. 2, pp. 65–70, 1979. [Online]. Available: https://www.jstor.org/stable/4615733
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” in 2017 IEEE International Conference on Computer Vision (ICCV), IEEE, Oct. 2017, pp. 618–626. doi: 10.1109/ICCV.2017.74.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Budi Juarto, Mochamad Haldi Widianto
This work is licensed under a Creative Commons Attribution 4.0 International License.
