MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation

Xiaoqing Guo, Chen Yang, Baopu Li, Yixuan Yuan*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

69 Citations (Scopus)

Abstract

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground truth labels to fully leverage unlabeled target data for model adaptation. However, the generated pseudo labels from the model optimized on the source domain inevitably contain noise due to the domain gap. To tackle this issue, we advance a MetaCorrection framework, where a Domain-aware Meta-learning strategy is devised to benefit Loss Correction (DMLC) for UDA semantic segmentation. In particular, we model the noise distribution of pseudo labels in target domain by introducing a noise transition matrix (NTM) and construct meta data set with domain-invariant source data to guide the estimation of NTM. Through the risk minimization on the meta data set, the optimized NTM thus can correct the noisy issues in pseudo labels and enhance the generalization ability of the model on the target data. Considering the capacity gap between shallow and deep features, we further employ the proposed DMLC strategy to provide matched and compatible supervision signals for different level features, thereby ensuring deep adaptation. Extensive experimental results highlight the effectiveness of our methoda against existing state-of-the-art methods on three benchmarks.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
EditorsLisa O’Conner
PublisherIEEE
Pages3926-3935
Number of pages10
ISBN (Electronic)9781665445092
ISBN (Print)9781665445108
DOIs
Publication statusPublished - 19 Jun 2021
Event2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States
Duration: 19 Jun 202125 Jun 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Country/TerritoryUnited States
CityVirtual, Online
Period19/06/2125/06/21

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation'. Together they form a unique fingerprint.

Cite this