Model Adaptive Learning: An Approach for Improving Object Recognition Efficiency
Corressponding author's email:
phuctd@gmail.comDOI:
https://doi.org/10.54644/jte.2024.1540Keywords:
Deep Learning, Adaptive Learning, Object Detection, Auto Vehice, Auto RobotAbstract
In recent years, research on artificial intelligence (AI) has experienced remarkable advancements. Many practical applications are the result of ongoing research, such as recognition technology, self-driving cars, translation, etc and most recently, the explosion of some AI-powered intelligent chatbots using large language models. Major corporations and research institutions worldwide are racing to develop AI models capable of the most accurate interaction based on user requests. However, despite achieving certain milestones, current AI models still fall short of the required intelligence to function similarly to the human brain. Based on research and experimentation, we propose an adaptive learning model that allows models to continuously learn during operation, select, and store previously acquired experiential knowledge to serve on-demand tasks. The proposed solution consists of four steps: (1) Initializing the initial recognition model; (2) Detection, recognition and collecting data from various instances of objects during operation based on object tracking; (3) Searching, selecting optimal models and hyperparameters on the discovered dataset; (4) Training and updating the model. The results of the proposed research could be a promising direction for the development of an adaptive learning model in advanced object recognition.
Downloads: 0
References
J. Achiam et al., "Gpt-4 technical report," arXiv preprint arXiv:2303.08774. 2023.
H. Bertrand et al., "Hyperparameter optimization of deep neural networks: Combining hyperband with Bayesian model selection," in Conférence sur l’Apprentissage Automatique, 2017, Art no. 10497518.
K. Blix and T. Eltoft, "Machine learning automatic model selection algorithm for oceanic chlorophyll-a content retrieval," Remote Sensing, vol. 10, p. 775, 2018. DOI: https://doi.org/10.3390/rs10050775
E. Bochinski et al., "Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms," in 2017 IEEE international conference on image processing (ICIP), 2017, pp. 3924-3928. DOI: https://doi.org/10.1109/ICIP.2017.8297018
C. Y. Wang, I. H. Yeh, and H. Y. M. Liao, "YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information," arXiv:2402.13616v2, 2024.
G. Dikov and J. Bayer, "Bayesian learning of neural network architectures," in The 22nd International Conference on Artificial Intelligence and Statistics, 2019, pp. 730-738.
T. Domhan et al., "Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves," in Twenty-fourth international joint conference on artificial intelligence, 2015, pp. 3460-3468.
A. C. Florea and R. Andonie, "Weighted random search for hyperparameter optimization," arXiv preprint arXiv:2004.01628, 2020.
R. Girshick, "Fast r-cnn," in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440-1448. DOI: https://doi.org/10.1109/ICCV.2015.169
R. Girshick et al., "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580-587. DOI: https://doi.org/10.1109/CVPR.2014.81
K. He et al., "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90
V. D. Hoang et al., "Robust human detection using multiple scale of cell based histogram of oriented gradients and adaboost learning," in International Conference on Computational Collective Intelligence, 2012, pp. 61-71. DOI: https://doi.org/10.1007/978-3-642-34630-9_7
C. Huang et al., "Learning policies for adaptive tracking with deep feature cascades," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 105-114. DOI: https://doi.org/10.1109/ICCV.2017.21
L. Kotthoff et al., "Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA," Journal of Machine Learning Research, vol. 18, pp. 1-5, 2017.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, pp. 1097-1105. 2012.
N. Q. K. Le et al., "Identification of clathrin proteins by incorporating hyperparameter optimization in deep learning and PSSM profiles," Computer methods and programs in biomedicine, vol. 177, pp. 81-88, 2019. DOI: https://doi.org/10.1016/j.cmpb.2019.05.016
L. Li and A. Talwalkar, "Random search and reproducibility for neural architecture search," in Uncertainty in artificial intelligence, 2020, pp. 367-377.
M. Long et al., "Transferable representation learning with deep adaptation networks," IEEE transactions on pattern analysis and machine intelligence, vol. 41, pp. 3071-3085, 2018. DOI: https://doi.org/10.1109/TPAMI.2018.2868685
H. Nam and B. Han, "Learning multi-domain convolutional neural networks for visual tracking," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4293-4302. DOI: https://doi.org/10.1109/CVPR.2016.465
A. Oksanen et al., "Artificial intelligence in fine arts: A systematic review of empirical research," Computers in Human Behavior: Artificial Humans, p. 100004, 2023. DOI: https://doi.org/10.1016/j.chbah.2023.100004
S. B. Punuri et al., "Efficient net-XGBoost: an implementation for facial emotion recognition using transfer learning," Mathematics, vol. 11, p. 776, 2023. DOI: https://doi.org/10.3390/math11030776
S. Raschka, "Model evaluation, model selection, and algorithm selection in machine learning," arXiv preprint arXiv:1811.12808, 2018.
D. Reis et al., "Real-time flying object detection with YOLOv8," arXiv preprint arXiv:2305.0997, 2023.
S. Ren et al., "Faster r-cnn: Towards real-time object detection with region proposal networks," in Advances in neural information processing systems, 2015, pp. 91-99.
Z. Song et al., "MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies," arXiv preprint arXiv:2403.01422, 2024.
C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9. DOI: https://doi.org/10.1109/CVPR.2015.7298594
F. M. Talaat and H. ZainEldin, "An improved fire detection approach based on YOLO-v8 for smart cities," Neural Computing and Applications, vol. 35, pp. 20939-20954, 2023. DOI: https://doi.org/10.1007/s00521-023-08809-1
J. Terven and D. C. Esparza, "A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond," arXiv preprint arXiv:2304.00501, 2023.
D. P. Tran and V. D. Hoang, "Adaptive learning based on tracking and ReIdentifying objects using convolutional neural network," Neural Processing Letters, vol. 50, pp. 263-282, 2019. DOI: https://doi.org/10.1007/s11063-019-10040-w
D. P. Tran et al., "Hyperparameter optimization for improving recognition efficiency of an adaptive learning system," IEEE Access, vol. 8, pp. 160569-160580, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3020930
S. Wang et al., "Single-Stage Pose Estimation and Joint Angle Extraction Method for Moving Human Body," Electronics, vol. 12, p. 4644, 2023. DOI: https://doi.org/10.3390/electronics12224644
X. Wang et al., "BL-YOLOv8: An improved road defect detection model based on YOLOv8," Sensors, vol. 23, p. 8361, 2023. DOI: https://doi.org/10.3390/s23208361
X. Zeng and G. Luo, "Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection," Health information science and systems, vol. 5, pp. 1-21, 2017. DOI: https://doi.org/10.1007/s13755-017-0023-z
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2024 Journal of Technical Education Science
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
