Papers › Context Prior for Scene Segmentation

Context Prior for Scene Segmentation

3 Apr 2020CVPR 2020 6arXiv:2004.01547archive 2025-07-28

Changqian Yu, Jingbo Wang, Changxin Gao, Gang Yu, Chunhua Shen, Nong Sang

Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding. In this work, we directly supervise the feature aggregation to distinguish the intra-class and inter-class context clearly. Specifically, we develop a Context Prior with the supervision of the Affinity Loss. Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior. The learned Context Prior extracts the pixels belonging to the same category, while the reversed prior focuses on the pixels of different classes. Embedded into a conventional deep CNN, the proposed Context Prior Layer can selectively capture the intra-class and inter-class contextual dependencies, leading to robust feature representation. To validate the effectiveness, we design an effective Context Prior Network (CPNet). Extensive quantitative and qualitative evaluations demonstrate that the proposed model performs favorably against state-of-the-art semantic segmentation approaches. More specifically, our algorithm achieves 46.3% mIoU on ADE20K, 53.9% mIoU on PASCAL-Context, and 81.3% mIoU on Cityscapes. Code is available at https://git.io/ContextPrior.

PaperPDFConference PDFCode

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

Code

ycszen/ContextPrior mentioned 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

Scene SegmentationScene UnderstandingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Understanding ADE20K val CPN(ResNet-101) Mean IoU 46.3 #1 of 1 Archive leaderboard report
Semantic Segmentation ADE20K CPN(ResNet-101) Validation mIoU 46.27 #179 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val CPN(ResNet-101) mIoU 46.27 #72 of 95 Archive leaderboard report
Semantic Segmentation Cityscapes test CPN(ResNet-101) Mean IoU (class) 81.3% #44 of 105 Archive leaderboard report
Semantic Segmentation PASCAL Context CPN(ResNet-101) mIoU 53.9 #38 of 66 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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