Articles
A Data-Aware Adaptive Model Compression Framework Integrating Group Attention Mechanisms and Reinforcement Learning for Efficient Neural Network Pruning
Downloads
Keywords
Model Compression
Neural Network Pruning
Reinforcement Learning
Group Attention
Article Usage Statistics
Live Metrics
Abstract Views
184
File Views
85
PDF
0
HTML
0
Other
85
Total
269
Article Usage Chart
Abstract
File Views
PDF
HTML
Other
Total
Abstract
The increasing deployment of deep neural networks in real-time and resource-constrained environments necessitates efficient model compression techniques without compromising predictive performance. This paper proposes a data-aware adaptive model compression framework that integrates group attention mechanisms with reinforcement learning (RL) for structured neural network pruning. The framework leverages data distribution characteristics to guide pruning decisions while employing group attention to identify semantically important feature groups. Reinforcement learning is utilized to dynamically learn optimal pruning policies across network layers. The proposed approach addresses limitations of static pruning strategies by enabling adaptive, data-driven compression tailored to task-specific requirements. Empirical analysis demonstrates improved trade-offs between accuracy and computational efficiency compared to traditional pruning methods. The framework is particularly relevant in domains such as plant disease detection, where deep learning models must operate efficiently on edge devices (Abayomi-Alli et al., 2021). The study contributes a unified perspective on integrating attention mechanisms and RL into compression pipelines, offering a scalable solution for modern deep learning applications.
Downloads
Download data is not yet available.
References
1. O. O. Abayomi-Alli, R. Damaševičius, S. Misra, and R. Maskeliūnas, “Cassava disease recognition from low-quality images using enhanced data augmentation model and deep learning,” Exp. Syst., vol. 38, no. 7, 2021, Art. no. e12746.
2. Almadhor, H. T. Rauf, M. I. U. Lali, R. Damaševičius, B. Alouffi, and A. Alharbi, “AI-driven framework for recognition of guava plant diseases through machine learning from DSLR camera sensor based high resolution imagery,” Sensors, vol. 21, no. 11, p. 3830, 2021.
3. J. G. A. Barbedo, “Factors influencing the use of deep learning for plant disease recognition,” Biosyst. Eng., vol. 172, pp. 84–91, Aug. 2018.
4. Z. Chen, R. Wu, Y. Lin, C. Li, S. Chen, Z. Yuan, S. Chen, and X. Zou, “Plant disease recognition model based on improved YOLOv5,” Agronomy, vol. 12, no. 2, p. 365, Jan. 2022.
5. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, “A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition,” Sensors, vol. 17, no. 9, p. 2022, 2017.
6. G. Ganesan and J. Chinnappan, “Hybridization of ResNet with YOLO classifier for automated paddy leaf disease recognition: An optimized model,” J. Field Robot., vol. 39, no. 7, pp. 1085–1109, Oct. 2022.
7. Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “YOLOX: Exceeding YOLO series in 2021,” 2021, arXiv:2107.08430.
8. D. Jiang, G. Li, C. Tan, L. Huang, Y. Sun, and J. Kong, “Semantic segmentation for multiscale target based on object recognition using the improved Faster-RCNN model,” Future Gener. Comput. Syst., vol. 123, pp. 94–104, Oct. 2021.
9. P. Jiang, Y. Chen, B. Liu, D. He, and C. Liang, “Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks,” IEEE Access, vol. 7, pp. 59069–59080, 2019.
10. N. Kundu, G. Rani, V. S. Dhaka, K. Gupta, S. C. Nayak, S. Verma, M. F. Ijaz, and M. Woźniak, “IoT and interpretable machine learning based framework for disease prediction in pearl millet,” Sensors, vol. 21, no. 16, p. 5386, Aug. 2021.
11. D. Li, R. Wang, C. Xie, L. Liu, J. Zhang, R. Li, F. Wang, M. Zhou, and W. Liu, “A recognition method for Rice plant diseases and pests video detection based on deep convolutional neural network,” Sensors, vol. 20, no. 3, p. 578, Jan. 2020.
12. Z. Lin, S. Mu, F. Huang, K. A. Mateen, M. Wang, W. Gao, and J. Jia, “A unified matrix-based convolutional neural network for fine-grained image classification of wheat leaf diseases,” IEEE Access, vol. 7, pp. 11570–11590, 2019.
13. M. P. Mathew and T. Y. Mahesh, “Leaf-based disease detection in bell pepper plant using YOLO v5,” Signal, Image Video Process., vol. 16, no. 3, pp. 841–847, Apr. 2022.
14. Pacal, A. Karaman, D. Karaboga, B. Akay, A. Basturk, U. Nalbantoglu, and S. Coskun, “An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets,” Comput. Biol. Med., vol. 141, Feb. 2022, Art. no. 105031.
15. J. Pan, L. Xia, Q. Wu, Y. Guo, Y. Chen, and X. Tian, “Automatic strawberry leaf scorch severity estimation via Faster R-CNN and few-shot learning,” Ecol. Informat., vol. 70, Sep. 2022, Art. no. 101706.
16. B. M. Patil and V. Burkpalli, “Segmentation of cotton leaf images using a modified chan vese method,” Multimedia Tools Appl., vol. 81, no. 11, pp. 15419–15437, May 2022.
17. Pramanik, S. K. Pal, J. Maiti, and P. Mitra, “Granulated RCNN and multi-class deep SORT for multi-object detection and tracking,” IEEE Trans. Emerg. Topics Comput. Intell., vol. 6, no. 1, pp. 171–181, Feb. 2022.
18. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 779–788.
19. Z. U. Rehman, M. A. Khan, F. Ahmed, R. Damaševičius, S. R. Naqvi, W. Nisar, and K. Javed, “Recognizing apple leaf diseases using a novel parallel real-time processing framework based on mask RCNN and transfer learning: An application for smart agriculture,” IET Image Processing, vol. 15, no. 10, pp. 2157–2168, 2021.
20. M. H. Saleem, S. Khanchi, J. Potgieter, and K. M. Arif, “Image-based plant disease identification by deep learning meta-architectures,” Plants, vol. 9, no. 11, p. 1451, Oct. 2020.
21. M. H. Saleem, J. Potgieter, and K. M. Arif, “Weed detection by faster RCNN model: An enhanced anchor box approach,” Agronomy, vol. 12, no. 7, p. 1580, Jun. 2022.
22. S. K. Upadhyay and A. Kumar, “A novel approach for Rice plant diseases classification with deep convolutional neural network,” Int. J. Inf. Technol., vol. 14, no. 1, pp. 185–199, Feb. 2022.
23. R. Wang, L. Jiao, C. Xie, P. Chen, J. Du, and R. Li, “S-RPN: Sampling-balanced region proposal network for small crop pest detection,” Comput. Electron. Agricult., vol. 187, Aug. 2021, Art. no. 106290.
24. X. Wang and J. Liu, “Tomato anomalies detection in greenhouse scenarios based on YOLO-dense,” Frontiers Plant Sci., vol. 12, p. 533, Apr. 2021.
25. J. Yao, Y. Wang, Y. Xiang, J. Yang, Y. Zhu, X. Li, S. Li, J. Zhang, and G. Gong, “Two-stage detection algorithm for kiwifruit leaf diseases based on deep learning,” Plants, vol. 11, no. 6, p. 768, Mar. 2022.
26. P. Zhang, L. Yang, and D. Li, “EfficientNet-B4-Ranger: A novel method for greenhouse cucumber disease recognition under natural complex environment,” Comput. Electron. Agricult., vol. 176, Sep. 2020, Art. no. 105652.
27. G. Zhou, W. Zhang, A. Chen, M. He, and X. Ma, “Rapid detection of Rice disease based on FCM-KM and faster R-CNN fusion,” IEEE Access, vol. 7, pp. 143190–143206, 2019.