• Home
  • Search
  • An Adaptive Dual-domain Feature Alignment Network for All-Day City Image Analysis
  • https://doi.org/10.1109/aibdf67964.2025.11440878Copy DOI Icon

An Adaptive Dual-domain Feature Alignment Network for All-Day City Image Analysis

  • Dec 26, 2025
  • Ying Qian +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

The vision of smart cities relies on robust, all-day automated image analysis systems to enhance urban management and public security. However, severe illumination variations between day and night present a significant challenge for tasks such as vehicle re-identification, where the same vehicle can appear drastically different due to lighting changes and nighttime glare. This impedes the reliability of continuous urban image analytics. To address this issue, we propose an Adaptive Dual-domain Feature Alignment Network (ADFA-Net). Our approach aligns vehicle features across time domains by learning illumination-invariant representations. ADFA-Net employs a dual-stream architecture with dedicated branches for processing day and night images. Each branch incorporates a glare suppression module to enhance feature quality. Crucially, features from both streams are adaptively fused at multiple semantic levels to construct a coherent and aligned feature space. Extensive evaluations on the cross-day-night benchmarks DN-348 and DN-Wild demonstrate the effectiveness of our model. On DN-348, ADFA-Net achieves 48.7% mAP and 72.2% Rank-1 accuracy. On the more challenging DN-Wild dataset, it attains 41.4% mAP and 51.0% Rank-1 accuracy.

Similar Papers
  • Research Article
  • Citations45

Vehicle Re-Identification Using Distance-Based Global and Partial Multi-Regional Feature Learning

  • Feb 04, 2020
  • IEEE Transactions on Intelligent Transportation Systems
  • Xu Chen +4
  • Book Chapter

Multi-Step Object Re-Identification on Edge Devices: A Pipeline for Vehicle Re-Identification

  • Dec 23, 2025
  • Tomass Zutis +5
  • Conference Article
  • Citations5

Assessing urban public security based on remote sensing and GIS

  • Jun 01, 2015
  • Xiaoxia Yan +2
  • Conference Article
  • Citations16

Attribute-guided Feature Extraction and Augmentation Robust Learning for Vehicle Re-identification

  • Jun 01, 2020
  • Chaoran Zhuge +4
  • Book Chapter
  • Citations1

Vehicle Re-identification via Spatio-temporal Multi-instance Learning

  • Jan 01, 2022
  • Xiang Yang +5
  • Research Article
  • Citations6

Vehicle Reidentification Based on Convolution and Vision Transformer Feature Fusion

  • Apr 01, 2024
  • IEEE MultiMedia
  • Rui Gong +4
  • Conference Article
  • Citations31

Vehicle re-identification by fusing multiple deep neural networks

  • Nov 01, 2017
  • Chao Cui +3
  • Conference Article
  • Citations40

A Structured Graph Attention Network for Vehicle Re-Identification

  • Oct 12, 2020
  • Yangchun Zhu +4
  • PDF
  • Research Article
  • Citations10

Local Feature-Aware Siamese Matching Model for Vehicle Re-Identification

  • Apr 03, 2020
  • Applied Sciences
  • Honglie Wang +5
  • PDF
  • Research Article
  • Citations2

Learning More in Vehicle Re-Identification: Joint Local Blur Transformation and Adversarial Network Optimization

  • Jul 25, 2022
  • Applied Sciences
  • Yanbing Chen +3
  • Research Article
  • Citations127

Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

  • Jun 10, 2020
  • Measurement Science and Technology
  • Jingjing Qian +3
  • Conference Article
  • Citations349

VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild

  • Jun 01, 2019
  • Yihang Lou +4
  • Research Article
  • Citations76

Multi-attribute adaptive aggregation transformer for vehicle re-identification

  • Jan 10, 2022
  • Information Processing & Management
  • Zhi Yu +4
  • Research Article
  • Citations2

A novel adaptive lightweight multimodal efficient feature inference network ALME-FIN for EEG emotion recognition.

  • Jan 13, 2025
  • Cognitive neurodynamics
  • Xiaoliang Guo +1
  • PDF
  • Research Article
  • Citations1

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

  • May 07, 2024
  • Applied Sciences
  • Yasong An +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.