Papers › MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with...
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation
Sumanth Udupa, Prajwal Gurunath, Aniruddh Sikdar, Suresh Sundaram
Deep neural networks have shown exemplary performance on semantic scene understanding tasks on source domains, but due to the absence of style diversity during training, enhancing performance on unseen target domains using only single source domain data remains a challenging task. Generation of simulated data is a feasible alternative to retrieving large style-diverse real-world datasets as it is a cumbersome and budget-intensive process. However, the large domain-specfic inconsistencies between simulated and real-world data pose a significant generalization challenge in semantic segmentation. In this work, to alleviate this problem, we propose a novel MultiResolution Feature Perturbation (MRFP) technique to randomize domain-specific fine-grained features and perturb style of coarse features. Our experimental results on various urban-scene segmentation datasets clearly indicate that, along with the perturbation of style-information, perturbation of fine-feature components is paramount to learn domain invariant robust feature maps for semantic segmentation models. MRFP is a simple and computationally efficient, transferable module with no additional learnable parameters or objective functions, that helps state-of-the-art deep neural networks to learn robust domain invariant features for simulation-to-real 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 | BDD100K val | MRFP+(Ours) Resnet50 | mIoU | 39.55 | #10 of 24 | Archive leaderboard | report |
| Semantic Segmentation | BDD100K val | Resnet50 | mIoU | 31.44 | #11 of 24 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | MRFP+(Ours) Resnet50 | mIoU | 42.4 | #97 of 99 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | Resnet50 | mIoU | 34.66 | #98 of 99 | Archive leaderboard | report |
| Semantic Segmentation | Mapillary val | MRFP+(Ours) Resnet50 | mIoU | 44.93 | #6 of 8 | Archive leaderboard | report |
| Semantic Segmentation | Mapillary val | Resnet50 | mIoU | 32.93 | #8 of 8 | Archive leaderboard | report |
| Semantic Segmentation | SYNTHIA | MRFP+(Ours) Resnet50 | mIoU | 30.22 | #2 of 3 | Archive leaderboard | report |
| Semantic Segmentation | SYNTHIA | Resnet50 | mIoU | 25.84 | #3 of 3 | 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