Papers › Co-Occurrent Features in Semantic Segmentation

Co-Occurrent Features in Semantic Segmentation

1 Jun 2019CVPR 2019 6archive 2025-07-28

Hang Zhang, Han Zhang, Chenguang Wang, Junyuan Xie

Recent work has achieved great success in utilizing global contextual information for semantic segmentation, including increasing the receptive field and aggregating pyramid feature representations. In this paper, we go beyond global context and explore the fine-grained representation using co-occurrent features by introducing Co-occurrent Feature Model, which predicts the distribution of co-occurrent features for a given target. To leverage the semantic context in the co-occurrent features, we build an Aggregated Co-occurrent Feature (ACF) Module by aggregating the probability of the co-occurrent feature with the co-occurrent context. ACF Module learns a fine-grained spatial invariant representation to capture co-occurrent context information across the scene. Our approach significantly improves the segmentation results using FCN and achieves superior performance 54.0% mIoU on Pascal Context, 87.2% mIoU on Pascal VOC 2012 and 44.89% mIoU on ADE20K datasets. The source code and complete system will be publicly available upon publication.

Paper PDF Code

Code

JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models tf report

zhanghang1989/PyTorch-Encoding pytorch 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

Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Segmentation	ADE20K	CFNet(ResNet-101)	Validation mIoU	44.89	#199 of 235	Archive leaderboard	report
Semantic Segmentation	PASCAL Context	CFNet (ResNet-101)	mIoU	54.0	#35 of 66	Archive leaderboard	report
Semantic Segmentation	PASCAL Context	CFNet (ResNet-50)	mIoU	51.5	#51 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 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution FCN Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual 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