• Home
  • Search
  • Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
  • Open Access IconOpen Access
  • Cite Icon27
  • https://doi.org/10.1007/978-3-031-20056-4_3Copy DOI Icon

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

  • Jan 1, 2022
  • Geon Lee +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation is to learn domain-invariant and discriminative features without target ground-truth labels. To this end, we propose a bi-directional pixel-prototype contrastive learning framework that minimizes intra-class variations of features for the same object class, while maximizing inter-class variations for different ones, regardless of domains. Specifically, our framework aligns pixel-level features and a prototype of the same object class in target and source images (i.e., positive pairs), respectively, sets them apart for different classes (i.e., negative pairs), and performs the alignment and separation processes toward the other direction with pixel-level features in the source image and a prototype in the target image. The cross-domain matching encourages domain-invariant feature representations, while the bidirectional pixel-prototype correspondences aggregate features for the same object class, providing discriminative features. To establish training pairs for contrastive learning, we propose to generate dynamic pseudo labels of target images using a non-parametric label transfer, that is, pixel-prototype correspondences across different domains. We also present a calibration method compensating class-wise domain biases of prototypes gradually during training. Experimental results on standard benchmarks including GTA5 \(\rightarrow \) Cityscapes and SYNTHIA \(\rightarrow \) Cityscapes demonstrate the effectiveness of our framework.KeywordsBi-directional contrastive learningDomain adaptive semantic segmentationDynamic pseudo label

Similar Papers
  • Research Article
  • Citations46

Class-Aware Domain Adaptation for Semantic Segmentation of Remote Sensing Images

  • Nov 17, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qingsong Xu +2
  • Conference Article
  • Citations5

Optimizing color transfer using color similarity measurement

  • Jun 01, 2016
  • Wei-Sung Chen +2
  • Research Article
  • Citations109

Generative Adversarial Network-Based Full-Space Domain Adaptation for Land Cover Classification From Multiple-Source Remote Sensing Images

  • Sep 23, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Shunping Ji +2
  • Research Article
  • Citations6

Fast color transfer from multiple images

  • Jun 01, 2017
  • Applied Mathematics-A Journal of Chinese Universities
  • Asad Khan +3
  • Research Article
  • Citations11

Uncertainty-weighted prototype active learning in domain adaptive semantic segmentation

  • Jan 04, 2024
  • Expert Systems with Applications
  • Zihao Dong +4
  • Research Article
  • Citations92

Source-free domain adaptation for image segmentation.

  • Nov 01, 2022
  • Medical Image Analysis
  • Mathilde Bateson +4
  • Research Article
  • Citations20

Prototype Guided Pseudo Labeling and Perturbation-based Active Learning for domain adaptive semantic segmentation

  • Dec 13, 2023
  • Pattern Recognition
  • Junkun Peng +4
  • Research Article
  • Citations10

Handling Open-Set Noise and Novel Target Recognition in Domain Adaptive Semantic Segmentation.

  • Aug 01, 2023
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xiaoqing Guo +3
  • Book Chapter
  • Citations1

Target Registration Based on Fusing Features of Visible and Two Wave Bands Infrared Images

  • Jan 01, 2021
  • Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
  • Junhua Yan +5
  • Book Chapter
  • Citations74

Source-Relaxed Domain Adaptation for Image Segmentation

  • Jan 01, 2020
  • Mathilde Bateson +4
  • Research Article
  • Citations554

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

  • Jan 06, 2021
  • International Journal of Computer Vision
  • Zhedong Zheng +1
  • Research Article
  • Citations23

Pseudo Label Rectification via Co-Teaching and Decoupling for Multisource Domain Adaptation in Semantic Segmentation

  • Jan 01, 2022
  • IEEE Access
  • So Jeong Park +5
  • PDF
  • Research Article
  • Citations16

Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation

  • Apr 29, 2021
  • Frontiers in Neuroscience
  • Kaisar Kushibar +6
  • Conference Article
  • Citations31

SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation

  • Jun 01, 2022
  • Xiaoqing Guo +3
  • Research Article
  • Citations36

SPGAN-DA: Semantic-Preserved Generative Adversarial Network for Domain Adaptive Remote Sensing Image Semantic Segmentation

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yansheng Li +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.