Papers › Semantic Correlation Promoted Shape-Variant Context for Segmentation

Semantic Correlation Promoted Shape-Variant Context for Segmentation

5 Sep 2019CVPR 2019 6arXiv:1909.02651archive 2025-07-28

Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang

Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context information from a predefined fixed region. In this work, we propose to generate a scale- and shape-variant semantic mask for each pixel to confine its contextual region. To this end, we first propose a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask. Using the inferred spatial scope of the contextual region, we propose a shape-variant convolution, of which the receptive field is controlled by the shape mask that varies with the appearance of input. In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region. Furthermore, this work also proposes a labeling denoising model to reduce wrong predictions caused by the noisy low-level features. Without bells and whistles, the proposed segmentation network achieves new state-of-the-arts consistently on the six public segmentation datasets.

PaperPDFConference PDFCode

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

Code

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

DenoisingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation COCO-Stuff test SVCNet (ResNet-101) mIoU 39.6% #15 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test SVCNet (ResNet-101) Mean IoU (class) 81.0% #47 of 105 Archive leaderboard report
Semantic Segmentation PASCAL Context SVCNet (ResNet-101) mIoU 53.2 #42 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