Bias Mitigation in Ensemble-Based Meat Freshness Classification Using Grad-CAM
- 28 March 2026
- journal article
- Published by Balkan Journal of Electrical & Computer Engineering (BAJECE) in Balkan Journal of Electrical and Computer Engineering
- Vol. 14, 74-82
Abstract
Visual biases in deep learning models, such as focusing on packaging trays instead of meat texture, reduce the reliability of computer vision systems in food safety applications. This study proposes a Grad-CAM-guided bias mitigation framework for multiclass meat freshness classification that combines explainable AI with a lightweight hybrid ensemble design. A MiniCAM attention module is integrated into MobileNetV2 to redirect model focus toward meat-specific visual cues, and its features are fused with complementary embeddings extracted from Xception. The final decision is obtained by combining the predictions of MobileNetV2 with classical classifiers (SVM and XGBoost) using test-time augmentation and grid-optimized weighted ensembling. The proposed framework achieves 99.78% accuracy on the held-out test set and 99.66% ± 0.23 average accuracy under 5-fold cross-validation, while maintaining real-time efficiency (4.3M parameters, 16.5 MB model size, and 825.1 FPS on a single GPU), and effectively suppresses non-informative background elements (e.g., packaging trays) as confirmed by Grad-CAM visualizations. These results demonstrate that integrating explainable bias mitigation with lightweight ensemble learning enables reliable and deployable meat freshness assessment for real-world food safety inspection.Keywords
Funding Information
- The authors declares that no funding was used in the study.
This publication has 16 references indexed in Scilit:
- Leveraging pre-trained computer vision models for accurate classification of meat freshnessFood Chemistry, 2025
- Detection and classification of meat freshness using an optimized deep learning methodFood Chemistry, 2025
- Single-Level Fusion for Enhancing Meat Quality Classification with Explainable AI2024
- ConvColor DL: Concatenated convolutional and handcrafted color features fusion for beef quality identificationFood Chemistry, 2024
- Meat Freshness State Prediction Using a Novel Fifteen Layered Deep Convolutional Neural Network2023
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009