Improved YOLOX object detection algorithm based on gradient difference adaptive learning rate optimization

被引：0
|
作者：
Song Y. [1 ]
Ge Q. [2 ,3 ,4 ]
Zhu J. [5 ]
Lu Z. [1 ]
机构：
[1] School of Artificial Intelligence, School of Future Technology, Nanjing University of Information Science and Technology, Nanjing
[2] School of Automation, Nanjing University of Information Science and Technology, Nanjing
[3] Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology （CICAEET）, Nanjing University of Information Science and Technology, Nanjing
[4] Jiangsu Province Engineering Research Center of Intelligent Meteorological Exploration Robot（C⁃IMER）, Nanjing University of Information Science and Technology, Nanjing
[5] College of Information Engineering, Henan University of Science and Technology, Luoyang
来源：
Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica | 2023年 / 44卷 / 14期
基金：
中国国家自然科学基金;
关键词：
neural network optimization; object detection; PASCAL VOC; RSOD; YOLOX;
D O I：
10.7527/S1000-6893.2022.27951
中图分类号：
学科分类号：
摘要：
Object detection has always been one of the most challenging problems in the field of computer vision，and is widely used in the tasks such as face recognition，autonomous driving and traffic detection. To further improve the performance of current mainstream object detection algorithms，this paper proposes an improved object detection algorithm based on YOLOX，and carries out experiments on the standard PASCAL VOC 07+12 and RSOD datasets. The YOLOX object detection algorithm is improved mainly through data enhancement，improving network structure and loss function. At the same time，an adaptive learning rate optimization algorithm based on gradient difference is proposed to train the improved YOLOX algorithm，which is also suitable for optimization of other neural networks. Experiments are carried out on PASCAL VOC 07+12 standard data sets. Results show that the AP of the improved YOLOX-S algorithm is increased from 61. 63% to 66. 35% compared with that of the original YOLOX-S algorithm. The improvement effect is obvious. Experiments are also carried out on the RSOD standard data set. The results show that the AP of the improved YOLOX-S algorithm is increased from 69. 4% to 73. 2% on the RSOD data set，compared with those of other mainstream YOLO series algorithms. The improvement effect is also significant. Experiments show effective improvement of YOLOX’s object detection. © 2023 AAAS Press of Chinese Society of Aeronautics and Astronautics. All rights reserved.
引用
收藏
相关论文
共 38 条
  • [21] GRAVES A., Generating sequences with recurrent neural networks［DB/OL］, (2013)
  • [22] Adam D P，BA J., A method for stochastic optimization［DB/OL］, (2014)
  • [23] LUO L C, LIU Y，, Et al., Adaptive gradient methods with dynamic bound of learning rate［DB/ OL］, (2019)
  • [24] ZHUANG J，, TANG T，, DING Y，, Et al., Adabelief optimi-zer：Adapting stepsizes by the belief in observed gradients［J］, Advances in Neural Information Processing Systems, 33, pp. 18795-18806, (2020)
  • [25] SHAO Z, LIN T., A new adaptive gradient method with gradient decomposition［DB/OL］
  • [26] ZHANG H Y，, CISSE M，, DAUPHIN Y N，, Et al., Mixup：Beyond empirical risk minimization［DB/OL］, (2017)
  • [27] DUBEY S R，, CHAKRABORTY S，, ROY S K, Et al., diffGrad：An optimization method for convolutional neural networks［J］, IEEE Transactions on Neural Networks and Learning Systems, 31, 11, pp. 4500-4511, (2020)
  • [28] ELFWING S，, UCHIBE E，, DOYA K., Sigmoid-weighted linear units for neural network function approximation in reinforcement learning［J］, Neural Networks, 107, pp. 3-11, (2018)
  • [29] GOYAL P, Et al., Focal loss for dense object detection［C］, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 318-327, (2018)
  • [30] EVERINGHAM M, VAN GOOL L，, WILLIAMS C K I, Et al., The pascal visual object classes（VOC）challenge ［J］, International Journal of Computer Vision, 88, 2, pp. 303-338, (2010)
1234