Search for collections on FTS Digilib

Leakage-Aware Cross-Dataset Multi-Task Learning for Shrimp Disease Recognition and Biomass Estimation

Juarto, Budi and Widianto, Mochamad Haldi (2026) Leakage-Aware Cross-Dataset Multi-Task Learning for Shrimp Disease Recognition and Biomass Estimation. Journal of Computing Theories and Applications, 4 (2). pp. 731-748. ISSN 3024-9104

[thumbnail of 17815-Article Text-64709-2-10-20261109.pdf] Text
17815-Article Text-64709-2-10-20261109.pdf - Published Version
Available under License Creative Commons Attribution.

Download (759kB)

Abstract

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.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Depositing User: dl fts
Date Deposited: 11 Nov 2026 06:26
Last Modified: 11 Nov 2026 06:26
URI: https://dl.futuretechsci.org/id/eprint/232

Actions (login required)

View Item
View Item