Papers › Improving Semantic Segmentation via Video Propagation and Label Relaxation

Improving Semantic Segmentation via Video Propagation and Label Relaxation

4 Dec 2018CVPR 2019 6arXiv:1812.01593archive 2025-07-28

Yi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks. We exploit video prediction models' ability to predict future frames in order to also predict future labels. A joint propagation strategy is also proposed to alleviate mis-alignments in synthesized samples. We demonstrate that training segmentation models on datasets augmented by the synthesized samples leads to significant improvements in accuracy. Furthermore, we introduce a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries. Our proposed methods achieve state-of-the-art mIoUs of 83.5% on Cityscapes and 82.9% on CamVid. Our single model, without model ensembles, achieves 72.8% mIoU on the KITTI semantic segmentation test set, which surpasses the winning entry of the ROB challenge 2018. Our code and videos can be found at https://nv-adlr.github.io/publication/2018-Segmentation.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

NVIDIA/semantic-segmentation mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hierarchical Multi-Scale Attention for Semantic Segmentation (arXiv:2005.10821; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
YeLyuUT/SSeg mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ganlumomo/mtl-segmentation mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ganlumomo/semantic-segmentation mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tobiasriedlinger/uncertainty-gradients-seg mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

SegmentationSemantic SegmentationVideo Propagation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation CamVid DeepLabV3Plus + SDCNetAug Mean IoU 81.7 #6 of 21 Archive leaderboard report
Semantic Segmentation KITTI Semantic Segmentation DeepLabV3Plus + SDCNetAug Category IoU 88.99 #2 of 7 Archive leaderboard report
Semantic Segmentation KITTI Semantic Segmentation DeepLabV3Plus + SDCNetAug Category iIoU 75.26 #2 of 7 Archive leaderboard report
Semantic Segmentation KITTI Semantic Segmentation DeepLabV3Plus + SDCNetAug Mean IoU (class) 72.83 #2 of 7 Archive leaderboard report
Semantic Segmentation KITTI Semantic Segmentation DeepLabV3Plus + SDCNetAug class iIoU 48.68 #2 of 7 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