• Home
  • Search
  • A One-Stage Domain Adaptation Network With Image Alignment for Unsupervised Nighttime Semantic Segmentation.
  • Cite Icon57
  • https://doi.org/10.1109/tpami.2021.3138829Copy DOI Icon

A One-Stage Domain Adaptation Network With Image Alignment for Unsupervised Nighttime Semantic Segmentation.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, we tackle the problem of semantic segmentation for nighttime images that plays an equally important role as that for daytime images in autonomous driving, but is also much more challenging due to very poor illuminations and scarce annotated datasets. It can be treated as an unsupervised domain adaptation (UDA) problem, i.e., applying other labeled dataset taken in the daytime to guide the network training meanwhile reducing the domain shift, so that the trained model can generalize well to the desired domain of nighttime images. However, current general-purpose UDA approaches are insufficient to address the significant appearance difference between the day and night domains. To overcome such a large domain gap, we propose a novel domain adaptation network "DANIA" for nighttime semantic image segmentation by leveraging a labeled daytime dataset (the source domain) and an unlabeled dataset that contains coarsely aligned day-night image pairs (the target daytime and nighttime domains). These three domains are used to perform a multi-target adaptation via adversarial training in the network. Specifically, for the unlabeled day-night image pairs, we use the pixel-level predictions of static object categories on a daytime image as a pseudo supervision to segment its counterpart nighttime image. We also include a step of image alignment to relieve the inaccuracy caused by the misalignment between day-night image pairs by estimating a flow to refine the pseudo supervision produced by daytime images. Finally, a re-weighting strategy is applied to further improve the predictions, especially boosting the prediction accuracy of small objects. The proposed DANIA is a one-stage adaptation framework for nighttime semantic segmentation, which does not train additional day-night image transfer models as a separate pre-processing stage. Extensive experiments on Dark Zurich and Nighttime Driving datasets show that our DANIA achieves state-of-the-art performance for nighttime semantic segmentation.

Similar Papers
  • Conference Article
  • Citations178

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

  • Jun 01, 2021
  • Xinyi Wu +4
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations180

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation.

  • Dec 18, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Christos Sakaridis +2
  • Research Article
  • Citations17

DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuxiang Cai +4
  • Conference Article
  • Citations284

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

  • Oct 01, 2019
  • Christos Sakaridis +2
  • Research Article
  • Citations56

Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation Using Region and Category Adaptive Domain Discriminator

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xiaoshu Chen +2
  • Dissertation
  • Citations2

Unsupervised domain adaptation for LiDAR segmentation

  • Jan 01, 2022
  • Lingdong Kong
  • Book Chapter
  • Citations55

Unsupervised Monocular Depth Estimation for Night-Time Images Using Adversarial Domain Feature Adaptation

  • Jan 01, 2020
  • Madhu Vankadari +4
  • Book Chapter
  • Citations131

Spatial Attention Pyramid Network for Unsupervised Domain Adaptation

  • Jan 01, 2020
  • Congcong Li +6
  • Conference Article
  • Citations2

Unsupervised Domain Extension for Nighttime Semantic Segmentation in Urban Scenes

  • Jan 01, 2021
  • Sebastian Scherer +3
  • Research Article
  • Citations3

Unsupervised global-local domain adaptation with self-training for remote sensing image semantic segmentation

  • Jan 20, 2025
  • International Journal of Remote Sensing
  • Junbo Zhang +3
  • Research Article
  • Citations64

Affinity Space Adaptation for Semantic Segmentation Across Domains.

  • Sep 26, 2020
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Wei Zhou +5
  • PDF
  • Research Article
  • Citations39

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation with Transformer

  • Oct 03, 2022
  • Remote Sensing
  • Weitao Li +3
  • Research Article
  • Citations2

Optimal transport-based domain adaptation for semantic segmentation of remote sensing images

  • Jan 16, 2024
  • International Journal of Remote Sensing
  • Ziyang Shen +3
  • Research Article
  • Citations55

Semantic Image Segmentation: Two Decades of Research

  • Oct 19, 2022
  • Foundations and Trends® in Computer Graphics and Vision
  • Gabriela Csurka +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.