ETM: Effective Tuning Method based on Multi-objective and Knowledge Transfer in Image Recognition

Weichun Liu, Chenglin Zhao
2021 IEEE Access  
With the widespread application of machine learning and deep learning, image recognition has been continuously developed. However, there are still huge challenges in the use of machine learning and deep learning. The tuning processes of algorithms are critical and challenging for their performance. Although there have been many previous works to improve the final accuracy of the recognition algorithms through tuning, these works cannot consider some indicators that are also very important in
more » ... actual environment (such as latency, central processing unit (cpu) utilization) in the tuning. In this paper, we propose an effective tuning method based on multi-objective and knowledge transfer, which is solved the above limitations in the image recognition. Specifically, we first use an agent to automatically tune the recognition algorithms, and combine the prediction accuracy and the running latency of each episode as a multiobjective reward signal to guide the update of the internal parameters of the agent. In this way, the agent can continuously select the better algorithm configuration to improve prediction performance. In addition, we improve the efficiency of the above tuning process by transferring knowledge. To do that, we can learn the meta parameters from other small-scale tasks to initialize the agent. In the experiments, we apply the proposed method to tune the eXtreme Gradient Boosting and random forest on 57 image recognition tasks and convolutional neural network on 2 tasks. The experimental results verify that the proposed method achieves average accuracy rankings of 1.92, 1.42 and 1.71 on three algorithms to be optimized, respectively. Especially in terms of latency performance, the proposed method performs best on all the tasks (57 data sets) on the three algorithms to be optimized. In addition, we verify the various components of the proposed method through ablation experiments. INDEX TERMS Image recognition, machine learning, deep learning, tuning, multi-objective, knowledge transfer. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ VOLUME 9, 2021 WEICHUN LIU received the M.S. degree in communication and information system from Zhengzhou University, in 2007, and the Ph.D. degree in information and communication engineering from the National University of Defense Technology, in 2020. He is currently an Associate Professor with the School of Information Engineering, Shaoyang University. His research interests include computer vision, machine learning, and computer graphics. CHENGLIN ZHAO is currently a Full Professor with the School of Information Engineering, Shaoyang University, where he is also a Master's Supervisor and the Dean. His research interests include image processing, machine vision, artificial intelligence, computer graphics, and scientific visualization.
doi:10.1109/access.2021.3062366 fatcat:qx4wkbh6jjfzzabjxh3pycevny