GRTR : Gradient Rebalanced Traffic Sign Recognition for Autonomous Vehicles

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

8 Scopus Citations
View graph of relations


  • Kehua Guo
  • Zheng Wu
  • Sheng Ren
  • Xiaokang Zhou
  • Thippa Reddy Gadekallu
  • Entao Luo
  • Chao Liu

Related Research Unit(s)


Original languageEnglish
Number of pages13
Journal / PublicationIEEE Transactions on Automation Science and Engineering
Online published2 May 2023
Publication statusOnline published - 2 May 2023


Traffic sign recognition is a crucial aspect of autonomous vehicle research, and deep learning techniques have significantly contributed to its progress. Nevertheless, the distribution of traffic sign information in natural complex road conditions is long-tailed, and traffic sign identification in complex road conditions has become a significant barrier to autonomous vehicle applications. The imbalanced distribution of information on the dataset migrates to the feature space during training, resulting in imbalanced classifier prediction. In this paper, we propose the gradient rebalanced traffic sign recognition (GRTR) method to address this problem for the first time. GRTR first evaluates the prediction and classification bias of the classifier using the fitted deviation between the model’s output probability and the ground-truth distributions. Then, GRTR dynamically adjusts the correction and compensation factors following the classifier’s prediction and classification biases. GRTR rebalances the positive and negative sample gradients for each category based on the synergistic effect of the correction and compensation factors to prevent the transfer of distribution imbalance and to significantly enhance the performance of the traffic sign classifier under difficult road conditions. Experimental results demonstrate that our GRTR achieves state-of-the-art performance on long-tailed traffic sign and multilabel datasets. Note to Practitioners—Most traffic sign recognition algorithms are still designed based on the assumption of a balanced distribution of traffic signs in the dataset. Real-world autonomous vehicles require traffic sign recognition on datasets with severely imbalanced distributions. This paper proposes a general approach to solving the long-tailed traffic sign recognition problem. © 2023 IEEE.

Research Area(s)

  • Autonomous vehicles, Convolutional neural networks, long-tailed learning, Predictive models, rebalancing method, Roads, Tail, Task analysis, traffic sign recognition, Training