Papers › D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution...

D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction

8 Dec 2018CVPR 2018 2018 12archive 2025-07-28

Lichen Zhou, Chuang Zhang, Ming Wu

Road extraction is a fundamental task in the field of remote sensing which has been a hot research topic in the past decade. In this paper, we propose a semantic segmentation neural network, named D-LinkNet, which adopts encoderdecoder structure, dilated convolution and pretrained encoder for road extraction task. The network is built with LinkNet architecture and has dilated convolution layers in its center part. Linknet architecture is efficient in computation and memory. Dilation convolution is a powerful tool that can enlarge the receptive field of feature points without reducing the resolution of the feature maps. In the CVPR DeepGlobe 2018 Road Extraction Challenge, our best IoU scores on the validation set and the test set are 0.6466 and 0.6342 respectively.

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

Road SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Road Segmentation DeepGlobe D-LinkNet IoU 0.6412 #2 of 3 Archive leaderboard report
Semantic Segmentation BJRoad D-LinkNet IoU 57.96 #7 of 11 Archive leaderboard report
Semantic Segmentation Porto D-LinkNet IoU 70.20 #6 of 6 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