Papers › MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

2 Dec 2022CVPR 2023 1arXiv:2212.01322archive 2025-07-28

Lukas Hoyer, Dengxin Dai, Haoran Wang, Luc van Gool

In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar visual appearance on the target domain as no ground truth is available to learn the slight appearance differences. To address this problem, we propose a Masked Image Consistency (MIC) module to enhance UDA by learning spatial context relations of the target domain as additional clues for robust visual recognition. MIC enforces the consistency between predictions of masked target images, where random patches are withheld, and pseudo-labels that are generated based on the complete image by an exponential moving average teacher. To minimize the consistency loss, the network has to learn to infer the predictions of the masked regions from their context. Due to its simple and universal concept, MIC can be integrated into various UDA methods across different visual recognition tasks such as image classification, semantic segmentation, and object detection. MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA. For instance, MIC achieves an unprecedented UDA performance of 75.9 mIoU and 92.8% on GTA-to-Cityscapes and VisDA-2017, respectively, which corresponds to an improvement of +2.1 and +3.0 percent points over the previous state of the art. The implementation is available at https://github.com/lhoyer/MIC.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lhoyer/mic officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationImage ClassificationImage-to-Image TranslationObject DetectionSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Cityscapes to ACDC MIC mIoU 70.4 #6 of 16 Archive leaderboard report
Domain Adaptation GTA5 to Cityscapes MIC mIoU 75.9 #4 of 28 Archive leaderboard report
Domain Adaptation Office-Home MIC Accuracy 86.2 #6 of 29 Archive leaderboard report
Domain Adaptation SYNTHIA-to-Cityscapes MIC mIoU 67.3 #5 of 33 Archive leaderboard report
Domain Adaptation VisDA2017 MIC Accuracy 92.8 #3 of 28 Archive leaderboard report
Image-to-Image Translation Cityscapes-to-Foggy Cityscapes MIC mAP 47.6 #1 of 6 Archive leaderboard report
Image-to-Image Translation GTAV-to-Cityscapes Labels MIC mIoU 75.9 #1 of 22 Archive leaderboard report
Image-to-Image Translation SYNTHIA-to-Cityscapes MIC mIoU (13 classes) 74.0 #2 of 28 Archive leaderboard report
Semantic Segmentation Dark Zurich MIC mIoU 60.2 #3 of 14 Archive leaderboard report
Semantic Segmentation GTAV-to-Cityscapes Labels MIC mIoU 75.9 #1 of 12 Archive leaderboard report
Semantic Segmentation SYNTHIA-to-Cityscapes MIC Mean IoU 67.3 #2 of 7 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels HRDA+MIC mIoU 75.9 #2 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes MIC MIoU (13 classes) 74.0 #3 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes MIC MIoU (16 classes) 67.3 #3 of 38 Archive leaderboard report
Unsupervised Domain Adaptation Cityscapes to Foggy Cityscapes MIC mAP@0.5 47.6 #5 of 22 Archive leaderboard report
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels MIC mIoU 75.9 #1 of 20 Archive leaderboard report
Unsupervised Domain Adaptation SYNTHIA-to-Cityscapes MIC mIoU 67.3 #4 of 23 Archive leaderboard report
Unsupervised Domain Adaptation SYNTHIA-to-Cityscapes MIC mIoU (13 classes) 74.0 #4 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections