ECR-MobileNet: An Imbalanced Largemouth Bass Parameter Prediction Model with Adaptive Contrastive Regression and Dependency-Graph Pruning
Open Access
Abstract
The precise, non-destructive monitoring of fish length and weight is a core technology for advancing intelligent aquaculture. However, this field faces dual challenges: traditional contact-based measurements induce stress and yield loss. In addition, existing computer vision methods are hindered by prediction biases from imbalanced data and the deployment bottleneck of balancing high accuracy with model lightweighting. This study aims to overcome these challenges by developing an efficient and robust deep learning framework. We propose ECR-MobileNet, a lightweight framework built on MobileNetV3-Small. It features three key innovations: an efficient channel attention (ECA) module to enhance feature discriminability, an original adaptive multi-scale contrastive regression (AMCR) loss function that extends contrastive learning to multi-dimensional regression for length and weight simultaneously to mitigate data imbalance, and a dependency-graph-based (DepGraph) structured pruning technique that synergistically optimizes model size and performance. On our multi-scene largemouth bass dataset, the pruned ECR-MobileNet-P model comprehensively outperformed 14 mainstream benchmarks. It achieved an R2 of 0.9784 and a root mean square error (RMSE) of 0.4296 cm for length prediction, as well as an R2 of 0.9740 and an RMSE of 0.0202 kg for weight prediction. The model’s parameter count is only 0.52 M, with a computational load of 0.07 giga floating-point operations per second (GFLOPs) and a CPU latency of 10.19 ms, achieving Pareto optimality. This study provides an edge-deployable solution for stress-free biometric monitoring in aquaculture and establishes an innovative methodological paradigm for imbalanced regression and task-oriented model compression.Keywords
Funding Information
- Provincial Key Research and Development Program (2023NK1020)
This publication has 29 references indexed in Scilit:
- Genetic analysis of swimming performance in rainbow trout (Oncorhynchus mykiss) using image traits derived from deep learningAquaculture, 2025
- A review of deep learning-based stereo vision techniques for phenotype feature and behavioral analysis of fish in aquacultureArtificial Intelligence Review, 2024
- A video object segmentation-based fish individual recognition method for underwater complex environmentsEcological Informatics, 2024
- A novel automated approach for fish biomass estimation in turbid environments through deep learning, object detection, and regressionEcological Informatics, 2024
- Fully automatic system for fish biomass estimation based on deep neural networkEcological Informatics, 2023
- The optimal feeding frequency for largemouth bass (Micropterus salmoides) reared in pond and in-pond-racewayAquaculture, 2022
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- Deep learning in agriculture: A surveyComputers and Electronics in Agriculture, 2018
- Measurement error in geometric morphometricsWilhelm Roux' Archiv für Entwicklungsmechanik der Organismen, 2016
- The use of computer vision technologies in aquaculture – A reviewComputers and Electronics in Agriculture, 2012