• Home
  • Search
  • Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
  • Cite Icon554
  • https://doi.org/10.1007/s11263-020-01395-yCopy DOI Icon

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

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

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. Yet the pseudo labels of the target-domain data are usually predicted by the model trained on the source domain. Thus, the generated labels inevitably contain the incorrect prediction due to the discrepancy between the training domain and the test domain, which could be transferred to the final adapted model and largely compromises the training process. To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation. Given the input image, the model outputs the semantic segmentation prediction as well as the uncertainty of the prediction. Specifically, we model the uncertainty via the prediction variance and involve the uncertainty into the optimization objective. To verify the effectiveness of the proposed method, we evaluate the proposed method on two prevalent synthetic-to-real semantic segmentation benchmarks, i.e., GTA5 \(\rightarrow \) Cityscapes and SYNTHIA \(\rightarrow \) Cityscapes, as well as one cross-city benchmark, i.e., Cityscapes \(\rightarrow \) Oxford RobotCar. We demonstrate through extensive experiments that the proposed approach (1) dynamically sets different confidence thresholds according to the prediction variance, (2) rectifies the learning from noisy pseudo labels, and (3) achieves significant improvements over the conventional pseudo label learning and yields competitive performance on all three benchmarks.

Similar Papers
  • Conference Article

Semi-supervised semantic segmentation via image-to-image translation

  • Apr 12, 2021
  • Feilong Wu +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
  • Research Article
  • Citations15

DualDA-Net: Dual-Head Rectification for Cross-Domain Object Detection of Remote Sensing

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yangguang Zhu +4
  • Research Article
  • Citations138

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xianfeng Li +6
  • Research Article
  • Citations13

Source-free domain adaptation via dynamic pseudo labeling and Self-supervision

  • Jul 22, 2024
  • Pattern Recognition
  • Qiankun Ma +7
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Conference Article
  • Citations5

Statistical and Geometrical Alignment using Metric Learning in Domain Adaptation

  • Jul 01, 2020
  • Rakesh Kumar Sanodiya +3
  • Research Article
  • Citations12

Domain adaptive remote sensing image semantic segmentation with prototype guidance

  • Mar 06, 2024
  • Neurocomputing
  • Wankang Zeng +6
  • Conference Article
  • Citations95

Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation

  • Oct 01, 2021
  • Yuxi Wang +2
  • Conference Article
  • Citations25

Self-Adaptation for Unsupervised Domain Adaptation

  • Oct 22, 2019
  • Xia Cui +1
  • Conference Article
  • Citations12

Pairwise Similarity Regularization for Adversarial Domain Adaptation

  • Oct 12, 2020
  • Haotian Wang +5
  • 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
  • Research Article
  • Citations2

Domain adaptation for semantic segmentation of road scenes via two-stage alignment of traffic elements

  • Oct 18, 2024
  • Neurocomputing
  • Yuan Gao +4
  • Research Article
  • Citations50

ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection.

  • Jan 01, 2022
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jihan Yang +4
  • Research Article
  • Citations4

CACP: Covariance-Aware Cross-Domain Prototypes for Domain Adaptive Semantic Segmentation

  • Jan 01, 2025
  • IEEE Transactions on Multimedia
  • Yanbing Xue +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.