Papers › SWRNet: A Deep Learning Approach for Small Surface Water Area Recognition Onboard Satellite
SWRNet: A Deep Learning Approach for Small Surface Water Area Recognition Onboard Satellite
Trong-An Bui, Pei-Jun Lee
This article proposes a deep learning approach for small surface water recognition using multispectral satellite imaging, which reduces the computational complexity by 18.66 times and increases the accuracy of surface water recognition by up to 14.1%. The proposed model uses near infrared combined with RGB spectral imagery to increase the accuracy of surface water recognition. In addition, since surface water only accounts for a small percentage of the remote sensing dataset, thus creating an imbalance problem, a proposed loss function is introduced to combine region-based and distribution-based loss. This article introduces an adaptive factor that automatically adjusts the weighting between distribution- and region-based loss functions. The proposed adaptive factor is determined based on the loss value of the previous training step. The mean intersection over union of surface water between predicted and ground truth regions is recorded as 0.80.
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 |
|---|---|---|---|---|---|---|---|
| 2D Semantic Segmentation | WorldFloods | SWRNet | Category mIoU | 0.789 | #1 of 1 | Archive leaderboard | report |
| 2D Semantic Segmentation | WorldFloods | SWRNet | GMac | 10.69 | #1 of 1 | Archive leaderboard | report |
| 2D Semantic Segmentation | WorldFloods | SWRNet | MParams | 1.95 | #1 of 1 | 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
Introduced by this paper: SWRNet
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