Papers › Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation...

Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation

25 Mar 2023CVPR 2023 1arXiv:2303.14361archive 2025-07-28

Shao-Yuan Lo, Poojan Oza, Sumanth Chennupati, Alejandro Galindo, Vishal M. Patel

Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data. However, the access to source data is often restricted or infeasible in real-world scenarios. Under the source data restrictive circumstances, UDA is less practical. To address this, recent works have explored solutions under the Source-Free Domain Adaptation (SFDA) setup, which aims to adapt a source-trained model to the target domain without accessing source data. Still, existing SFDA approaches use only image-level information for adaptation, making them sub-optimal in video applications. This paper studies SFDA for Video Semantic Segmentation (VSS), where temporal information is leveraged to address video adaptation. Specifically, we propose Spatio-Temporal Pixel-Level (STPL) contrastive learning, a novel method that takes full advantage of spatio-temporal information to tackle the absence of source data better. STPL explicitly learns semantic correlations among pixels in the spatio-temporal space, providing strong self-supervision for adaptation to the unlabeled target domain. Extensive experiments show that STPL achieves state-of-the-art performance on VSS benchmarks compared to current UDA and SFDA approaches. Code is available at: https://github.com/shaoyuanlo/STPL

PaperPDFConference PDFCode

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

Code

shaoyuanlo/stpl officialmentioned in paperpytorch 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

Contrastive LearningDomain AdaptationSemantic SegmentationSource-Free Domain AdaptationUnsupervised Domain AdaptationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation SYNTHIA-to-Cityscapes STPL mIoU 51.8 #18 of 33 Archive leaderboard report
Domain Adaptation VIPER-to-Cityscapes STPL mIoU 52.5 #1 of 1 Archive leaderboard report
Source-Free Domain Adaptation SYNTHIA-to-Cityscapes STPL mIoU 51.8 #1 of 1 Archive leaderboard report
Source-Free Domain Adaptation VIPER-to-Cityscapes STPL mIoU 52.5 #1 of 1 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