MECT-MobileViT: A Lightweight Fish Weight Prediction Model Based on Dual-View Morphological Feature Fusion and Anti-Interference Attention
Animals · 05.07.2026 · 16 (13) · 2076
DOI: 10.3390/ani16132076 ↗Kurz gefasst
Fachartikel in der Zeitschrift Animals, online erschienen am 05.07.2026. Verfasst von Yi Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Hunan Province of China, Key Research and Development Program of Hunan, provincial key research and development program.
Abstract (Originalsprache)
In intensive aquaculture, non-invasive real-time monitoring of morphological traits and body weight of largemouth bass (Micropterus salmoides) is essential for precision feeding and yield estimation. Manual measurement is laborious and stressful, whereas vision-based methods are challenged by insufficient dual-view feature fusion, poor robustness to underwater noise, and over-parameterized models unsuitable for edge deployment. To address these issues, a lightweight framework, MECT-MobileViT, is proposed based on MobileViT-xxs. A Morphometric-Guided Multi-Scale Fusion module is designed to couple physical priors with dual-branch visual features, strengthening shape–weight association. An ECA-NL attention block employing instance normalization, GLU gating, and threshold filtering is embedded to enhance feature robustness against visual disturbances typical in aquaculture and to accentuate critical morphological features. A three-stage synergistic pruning strategy—attention head pruning, structured channel pruning, and depthwise separable attention substitution—is applied to achieve substantial compression while preserving representational capacity. Experiments on a self-built lateral–dorsal dual-view dataset show that the proposed model significantly outperforms mainstream benchmarks. The pruned version attains an R2 of 0.8266 and an RMSE of 16.4201, with less than 2% accuracy degradation relative to the best unpruned model, and contains only 7.34 M parameters. This study demonstrates a promising prototype for contactless, stress-free weight estimation in largemouth bass and offers new technical insights into feature fusion, noise suppression, and collaborative model compression for aquaculture visual perception.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China.
- College of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, China.
ORCID-Profile: Mingyu Tan
Förderung
- Key Research and Development Program of Hunan Province of China
- Key Research and Development Program of Hunan
- provincial key research and development program
- Postgraduate Scientific Research Innovation Project of Hunan Agriculture University
Zitieren
APA
Wang, Y., Tan, M., Deng, J., Yang, L., Wu, Y., Peng, H., Ouyang, C., Luo, Y., Hu, W., & Jiang, P. (2026). MECT-MobileViT: A Lightweight Fish Weight Prediction Model Based on Dual-View Morphological Feature Fusion and Anti-Interference Attention. Animals, 16(13), 2076. https://doi.org/10.3390/ani16132076
Vancouver
Wang Y, Tan M, Deng J, Yang L, Wu Y, Peng H, et al. MECT-MobileViT: A Lightweight Fish Weight Prediction Model Based on Dual-View Morphological Feature Fusion and Anti-Interference Attention. Animals. 2026;16(13):2076. doi:10.3390/ani16132076
BibTeX
@article{Wang2026,
author = {Wang, Yi and Tan, Mingyu and Deng, Jingtao and Yang, Lin and Wu, Yongjie and Peng, Hao and Ouyang, Cheng and Luo, Yahui and Hu, Wenwu and Jiang, Pin},
title = {MECT-MobileViT: A Lightweight Fish Weight Prediction Model Based on Dual-View Morphological Feature Fusion and Anti-Interference Attention},
journal = {Animals},
year = {2026},
volume = {16},
number = {13},
pages = {2076},
doi = {10.3390/ani16132076}
}
EUVIMED