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

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

7 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Subtitle of host publicationCVPR 2021
PublisherIEEE
Pages3926-3935
ISBN (Electronic)9781665445092
ISBN (Print)9781665445108
Publication statusPublished - 2021

Publication series

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

Conference

Title2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
LocationVirtual
Period19 - 25 June 2021

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 method against existing state-of-the-art methods on three benchmarks.

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

MetaCorrection : Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation. / Guo, Xiaoqing; Yang, Chen; Li, Baopu; Yuan, Yixuan.

Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2021. IEEE, 2021. p. 3926-3935 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review