Papers › All about Structure: Adapting Structural Information across Domains for Boosting...

All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation

26 Mar 2019CVPR 2019 6arXiv:1903.12212archive 2025-07-28

Wei-Lun Chang, Hui-Po Wang, Wen-Hsiao Peng, Wei-Chen Chiu

In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation. With the hypothesis that the structural content of images is the most informative and decisive factor to semantic segmentation and can be readily shared across domains, we propose a Domain Invariant Structure Extraction (DISE) framework to disentangle images into domain-invariant structure and domain-specific texture representations, which can further realize image-translation across domains and enable label transfer to improve segmentation performance. Extensive experiments verify the effectiveness of our proposed DISE model and demonstrate its superiority over several state-of-the-art approaches.

PaperPDFConference PDFCode

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

Code

a514514772/DISE-Domain-Invariant-Structure-Extraction officialmentioned in papermentioned on GitHubpytorchGPL-3.0 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

AllDomain AdaptationImage-to-Image TranslationSegmentationSemantic SegmentationSynthetic-to-Real TranslationTranslationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-to-Image Translation SYNTHIA-to-Cityscapes Domain Invariant Structure Extraction mIoU (13 classes) 41.5 #25 of 28 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels DISE mIoU 45.4 #60 of 73 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