Papers › Dual Super-Resolution Learning for Semantic Segmentation
Dual Super-Resolution Learning for Semantic Segmentation
Li Wang, Dong Li, Yousong Zhu, Lu Tian, Yi Shan
Current state-of-the-art semantic segmentation methods often apply high-resolution input to attain high performance, which brings large computation budgets and limits their applications on resource-constrained devices. In this paper, we propose a simple and flexible two-stream framework named Dual Super-Resolution Learning (DSRL) to effectively improve the segmentation accuracy without introducing extra computation costs. Specifically, the proposed method consists of three parts: Semantic Segmentation Super-Resolution (SSSR), Single Image Super-Resolution (SISR) and Feature Affinity (FA) module, which can keep high-resolution representations with low-resolution input while simultaneously reducing the model computation complexity. Moreover, it can be easily generalized to other tasks, e.g., human pose estimation. This simple yet effective method leads to strong representations and is evidenced by promising performance on both semantic segmentation and human pose estimation. Specifically, for semantic segmentation on CityScapes, we can achieve \geq2% higher mIoU with similar FLOPs, and keep the performance with 70% FLOPs. For human pose estimation, we can gain \geq2% mAP with the same FLOPs and maintain mAP with 30% fewer FLOPs. Code and models are available at https://github.com/wanglixilinx/DSRL.
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 |
|---|---|---|---|---|---|---|---|
| Crack Segmentation | khanhha's dataset - 4x upscaling (blind) | DSRL | AHD95 | 148.97 | #6 of 7 | Archive leaderboard | report |
| Crack Segmentation | khanhha's dataset - 4x upscaling (blind) | DSRL | Average IOU | 0.285 | #6 of 7 | Archive leaderboard | report |
| Crack Segmentation | khanhha's dataset - 4x upscaling (blind) | DSRL | HD95_min | 44.23 | #6 of 7 | Archive leaderboard | report |
| Crack Segmentation | khanhha's dataset - 4x upscaling (blind) | DSRL | IoU_max | 0.391 | #6 of 7 | 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