Lune

AAAI2022Top-tier venue

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

Wei-Ting Chen, I-Hsiang Chen, Chih-Yuan Yeh, Hao-Hsiang Yang, Jian-Jiun Ding, Sy-Yen Kuo

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 fogfree 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 semisupervised 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Vehiclemae: View-Asymmetry Mutual Learning for Vehicle Re-Identification Pre-Training Via Masked Autoencoders cites Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
  • Vehiclemae: View-Asymmetry Mutual Learning for Vehicle Re-Identification Pre-Training Via Masked Autoencoders cites TransReID: Transformer-based Object Re-Identification
  • Phase Consistent Ecological Domain Adaptation cites FDA: Fourier Domain Adaptation for Semantic Segmentation
  • FDA: Fourier Domain Adaptation for Semantic Segmentation cites Phase Consistent Ecological Domain Adaptation
  • RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations cites Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation
  • RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations cites Multi-Stage Progressive Image Restoration
  • RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations cites UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior
  • TransReID: Transformer-based Object Re-Identification cites Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
  • Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation cites UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior
  • UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior cites Multi-Stage Progressive Image Restoration
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Vehiclemae: View-Asymmetry Mutual Learning for Vehicle Re-Identification Pre-Training Via Masked AutoencodersQi Wang, Zeyu Zhang, Dong Wang, Di Gai et al.ICCV 2025 · 5 citations
  2. Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic SegmentationI-Hsiang Chen, Hua-En Chang, Wei-Ting Chen, Jenq-Neng Hwang et al.ICCV 2025 · 2 citations
  3. RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual DegradationsI-Hsiang Chen, Yu-Wei Liu, Tse-Yu Wu, Yu-Chien Chiang et al.CVPR 2026
  4. Curricular Contrastive Regularization for Physics-Aware Single Image DehazingYu Zheng, Jiahui Zhan, Shengfeng He, Junyu Dong et al.CVPR 2023
  5. UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion PriorI-Hsiang Chen, Wei-Ting Chen, Yu-Wei Liu, Yuan-Chun Chiang et al.CVPR 2025

Builds on6

  1. TransReID: Transformer-based Object Re-IdentificationShuting He, Hao Luo, Pichao Wang, Fan Wang et al.ICCV 2021 · 1,172 citations
  2. Phase Consistent Ecological Domain AdaptationYanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano SoattoCVPR 2020
  3. Parsing-Based View-Aware Embedding Network for Vehicle Re-IdentificationDechao Meng, Liang Li, Xuejing Liu, Yadong Li et al.CVPR 2020
  4. FDA: Fourier Domain Adaptation for Semantic SegmentationYanchao Yang, Stefano SoattoCVPR 2020
  5. Multi-Stage Progressive Image RestorationSyed Waqas Zamir, Aditya Arora, Salman H. Khan, Munawar Hayat et al.CVPR 2021

Related papers

  1. DualDis: A Dual Disentanglement Network for Vehicle Re-identificationWenying He, Feiyu Wang, Guangquan Xu, Yude Bai et al.WWW 2026
  2. Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and BeyondMing Li, Xinming Huang, Ziming ZhangICCV 2021 · 55 citations
  3. Real-World Person Re-Identification via Degradation Invariance LearningYukun Huang, Zheng-Jun Zha, Xueyang Fu, Richang Hong et al.CVPR 2020
  4. Day-Night Cross-domain Vehicle Re-identificationHongchao Li, Jingong Chen, Aihua Zheng, Yong Wu et al.CVPR 2024
  5. Optical Flow in Dense Foggy Scenes Using Semi-Supervised LearningWending Yan, Aashish Sharma, Robby T. TanCVPR 2020
Dusk over the sea between two cliffs drawn in fine vertical lines