Rohani, M., Farsi, H., Mohamadzadeh, S.. (1404). Advanced Race Classification Using Transfer Learning and Attention: Real-Time Metrics, Error Analysis, and Visualization in a Lightweight Deep Learning Model. فناوری آموزش, 13(2), 341-352. doi: 10.22061/jecei.2025.11318.793
M. Rohani; H. Farsi; S. Mohamadzadeh. "Advanced Race Classification Using Transfer Learning and Attention: Real-Time Metrics, Error Analysis, and Visualization in a Lightweight Deep Learning Model". فناوری آموزش, 13, 2, 1404, 341-352. doi: 10.22061/jecei.2025.11318.793
Rohani, M., Farsi, H., Mohamadzadeh, S.. (1404). 'Advanced Race Classification Using Transfer Learning and Attention: Real-Time Metrics, Error Analysis, and Visualization in a Lightweight Deep Learning Model', فناوری آموزش, 13(2), pp. 341-352. doi: 10.22061/jecei.2025.11318.793
Rohani, M., Farsi, H., Mohamadzadeh, S.. Advanced Race Classification Using Transfer Learning and Attention: Real-Time Metrics, Error Analysis, and Visualization in a Lightweight Deep Learning Model. فناوری آموزش, 1404; 13(2): 341-352. doi: 10.22061/jecei.2025.11318.793
Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran.
تاریخ دریافت: 08 مهر 1403،
تاریخ بازنگری: 17 دی 1403،
تاریخ پذیرش: 21 دی 1403
چکیده
Background and Objectives: Recent advancements in race classification from facial images have been significantly propelled by deep learning techniques. Despite these advancements, many existing methodologies rely on intricate models that entail substantial computational costs and exhibit slow processing speeds. This study aims to introduce an efficient and robust approach for race classification by utilizing transfer learning alongside a modified Efficient-Net model that incorporates attention-based learning. Methods: In this research, Efficient-Net is employed as the base model, applying transfer learning and attention mechanisms to enhance its efficacy in race classification tasks. The classifier component of Efficient-Net was strategically modified to minimize the parameter count, thereby enhancing processing speed without compromising classification accuracy. To address dataset imbalance, we implemented extensive data augmentation and random oversampling techniques. The modified model was rigorously trained and evaluated on a comprehensive dataset, with performance assessed through accuracy, precision, recall, and F1 score metrics. Results: The modified Efficient-Net model exhibited remarkable classification accuracy while significantly reducing computational demands on the UTK-Face and FairFace datasets. Specifically, the model achieved an accuracy of 88.19% on UTK-Face and 66% on FairFace, reflecting a 2% enhancement over the base model. Additionally, it demonstrated a 9-14% reduction in memory consumption and parameter count. Real-time evaluations revealed a processing speed 14% faster than the base model, alongside achieving the highest F1-score results, which underscores its effectiveness for practical applications. Furthermore, the proposed method enhanced test accuracy in classes with approximately 50% fewer training samples by about 5%. Conclusion: This study presents efficient race classification model grounded in a modified Efficient-Net that utilizes transfer learning and attention-based learning to attain state-of-the-art performance. The proposed approach not only sustains high accuracy but also ensures rapid processing speeds, rendering it ideal for real-time applications. The findings indicate that this lightweight model can effectively rival more complex and computationally intensive recent methods, providing a valuable asset for practical race classification endeavors.
