A Sea Clutter Suppression Method based on Neighborhood Self-supervised for Ship Detection in SAR Images
Bibliographic record
Abstract
Ship detection in Synthetic Aperture Radar (SAR) images plays a considerable role in ocean monitoring and maritime management. However, due to the complex distributions of sea clutter and the low signal-to-clutter ratio of targets, high-precision ship detection under strong sea clutters is still challenging. A sea clutter suppression method based on neighborhood pixels self-supervised is proposed in this paper for ship detection in SAR images, which comprises the sea clutter suppression stage and the ship detection stage. In the former stage, a Weibull-distribution-based image pre-processing is initially carried out to achieve zero mean normalization of SAR images. Then, a neighborhood sampler based on adjacent pixels of the sea clutter is designed to obtain independent and identically distributed paired image slices for training. Further, a self-supervised network based on U-Net is established with the sampled paired images as input for sea clutter suppression, which does not require any clean ships. In particular, a hybrid loss function including the reconstruction and regularization terms, is customized to ensure the network’s reconstruction and generalization abilities. In the latter stage, a YOLOv5-based detection network is adopted in sea clutter-suppressed images to improve the detection performance of weak ships under complex backgrounds. Experiments conducted on the Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) demonstrate the effectiveness of the proposed method, which achieves a 0.7% improvement in detection accuracy compared with typical detection algorithms.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".