Papers › Scene Segmentation with Dual Relation-aware Attention Network

Scene Segmentation with Dual Relation-aware Attention Network

5 Aug 2020TNNLS 2020 8archive 2025-07-28

Jun Fu, Jing Liu, Jie Jiang, Yong Li, Yongjun Bao, Hanqing Lu

In this article, we propose a Dual Relation-aware Attention Network (DRANet) to handle the task of scene segmentation. How to efficiently exploit context is essential for pixel-level recognition. To address the issue, we adaptively capture contextual information based on the relation-aware attention mechanism. Especially, we append two types of attention modules on the top of the dilated fully convolutional network (FCN), which model the contextual dependencies in spatial and channel dimensions, respectively. In the attention modules, we adopt a self-attention mechanism to model semantic associations between any two pixels or channels. Each pixel or channel can adaptively aggregate context from all pixels or channels according to their correlations. To reduce the high cost of computation and memory caused by the abovementioned pairwise association computation, we further design two types of compact attention modules. In the compact attention modules, each pixel or channel is built into association only with a few numbers of gathering centers and obtains corresponding context aggregation over these gathering centers. Meanwhile, we add a cross-level gating decoder to selectively enhance spatial details that boost the performance of the network. We conduct extensive experiments to validate the effectiveness of our network and achieve new state-of-the-art segmentation performance on four challenging scene segmentation data sets, i.e., Cityscapes, ADE20K, PASCAL Context, and COCO Stuff data sets. In particular, a Mean IoU score of 82.9% on the Cityscapes test set is achieved without using extra coarse annotated data.

PaperPDFCode

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

Scene SegmentationSegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K DRAN(ResNet-101) Validation mIoU 46.18 #181 of 235 Archive leaderboard report
Semantic Segmentation COCO-Stuff test DRAN(ResNet-101) mIoU 41.2% #10 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test DRAN(ResNet-101) WITH ONLY FINE ANNOTATED DATA Mean IoU (class) 82.9% #23 of 105 Archive leaderboard report
Semantic Segmentation PASCAL Context DRAN(ResNet-101) mIoU 55.4% #29 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.

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