Papers › Location-aware Upsampling for Semantic Segmentation
Location-aware Upsampling for Semantic Segmentation
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
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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