SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification

Authors

  • Wei-Ting Chen Graduate Institute of Electronics Engineering, National Taiwan University, Taiwan ASUS Intelligent Cloud Services, Taiwan
  • I-Hsiang Chen Department of Electrical Engineering, National Taiwan University, Taiwan
  • Chih-Yuan Yeh Department of Electrical Engineering, National Taiwan University, Taiwan
  • Hao-Hsiang Yang Department of Electrical Engineering, National Taiwan University, Taiwan
  • Jian-Jiun Ding Department of Electrical Engineering, National Taiwan University, Taiwan
  • Sy-Yen Kuo Department of Electrical Engineering, National Taiwan University, Taiwan

DOI:

https://doi.org/10.1609/aaai.v36i1.19911

Keywords:

Computer Vision (CV)

Abstract

Vehicle re-identification (ReID) has attracted considerable attention in computer vision. Although several methods have been proposed to achieve state-of-the-art performance on this topic, re-identifying vehicle in foggy scenes remains a great challenge due to the degradation of visibility. To our knowledge, this problem is still not well-addressed so far. In this paper, to address this problem, we propose a novel training framework called Semi-supervised Joint Defogging Learning (SJDL) framework. First, the fog removal branch and the re-identification branch are integrated to perform simultaneous training. With the collaborative training scheme, defogged features generated by the defogging branch from input images can be shared to learn better representation for the re-identification branch. However, since the fog-free image of real-world data is intractable, this architecture can only be trained on the synthetic data, which may cause the domain gap problem between real-world and synthetic scenarios. To solve this problem, we design a semi-supervised defogging training scheme that can train two kinds of data alternatively in each iteration. Due to the lack of a dataset specialized for vehicle ReID in the foggy weather, we construct a dataset called FVRID which consists of real-world and synthetic foggy images to train and evaluate the performance. Experimental results show that the proposed method is effective and outperforms other existing vehicle ReID methods in the foggy weather. The code and dataset are available in https://github.com/Cihsaing/SJDL-Foggy-Vehicle-Re-Identification--AAAI2022.

Downloads

Published

2022-06-28

How to Cite

Chen, W.-T., Chen, I.-H., Yeh, C.-Y., Yang, H.-H., Ding, J.-J., & Kuo, S.-Y. (2022). SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 347-355. https://doi.org/10.1609/aaai.v36i1.19911

Issue

Section

AAAI Technical Track on Computer Vision I