Papers › Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation...

Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

23 Jun 2021arXiv:2106.12413archive 2025-07-28

Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, Xiaoliang Meng

Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, and urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. Besides, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset. Code is available at https://github.com/WangLibo1995/GeoSeg.

PaperPDFCode

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

Code

WangLibo1995/GeoSeg officialmentioned in paperpytorch 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

Autonomous DrivingDecision MakingImage SegmentationLand Cover ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ISPRS Potsdam BANet Overall Accuracy 91.06 #13 of 20 Archive leaderboard report
Semantic Segmentation ISPRS Vaihingen BANet Overall Accuracy 90.5 #9 of 12 Archive leaderboard report
Semantic Segmentation UAVid BANet Mean IoU 64.6 #10 of 10 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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