Papers › Location-aware Upsampling for Semantic Segmentation

Location-aware Upsampling for Semantic Segmentation

13 Nov 2019arXiv:1911.05250archive 2025-07-28

Xiangyu He, Zitao Mo, Qiang Chen, Anda Cheng, Peisong Wang, Jian Cheng

Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into semantic segmentation. Based on this idea, we present a Location-aware Upsampling (LaU) that adaptively refines the interpolating coordinates with trainable offsets. Then, location-aware losses are established by encouraging pixels to move towards well-classified locations. An LaU is offset prediction coupled with interpolation, which is trained end-to-end to generate confidence score at each position from coarse to fine. Guided by location-aware losses, the new module can replace its plain counterpart (\textit{e.g.}, bilinear upsampling) in a plug-and-play manner to further boost the leading encoder-decoder approaches. Extensive experiments validate the consistent improvement over the state-of-the-art methods on benchmark datasets. Our code is available at https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation

PaperPDFCode

Code

HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation officialmentioned in papermentioned on GitHubpytorch 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

DecoderSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K LaU-regression-loss Test Score 56.32 #196 of 235 Archive leaderboard report
Semantic Segmentation ADE20K LaU-regression-loss Validation mIoU 45.02 #196 of 235 Archive leaderboard report
Semantic Segmentation ADE20K LaU-offset-loss Test Score 56.41 #201 of 235 Archive leaderboard report
Semantic Segmentation ADE20K LaU-offset-loss Validation mIoU 44.55 #201 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val LaU-regression-loss mIoU 45.02 #84 of 95 Archive leaderboard report
Semantic Segmentation PASCAL Context LaU-regression-loss (ResNet-101) mIoU 53.9 #39 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 BlockConvolutionDice LossGlobal 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