Maritime Vessel Classification in Low-Resolution Synthetic Aperture Radar Imagery
Bibliographic record
Abstract
The ability to accurately classify maritime vessel types in low-resolution synthetic aperture radar (SAR) imagery is crucial for various applications, such as naval operations, maritime surveillance, and search and rescue missions. This paper proposes the development of advanced machine learning algorithms for classifying vessel types in low-resolution SAR imagery, addressing the challenges of variability in image resolution, contrast, and clutter noise. Our work focuses on overcoming visual ambiguity in vessel labels, variations in clutter due to different beam modes, and complexities introduced by different polarization modes using the DRDC-R2 dataset. This paper presents several contributions, including the proposal of an enhanced version of a PyramidNet model, a novel DualPyramidNet classifier to capture features from pairs of dual-polarized SAR images, and the integration of an incidence angle prediction output layer into the DualPyramidNet architecture. Furthermore, this paper introduces a domain adaptation technique to align the distribution of clutter variations caused by different incidence angles, enhancing the model's generalization capabilities. Our experimental results demonstrate enhanced performance of vessel type classification and incidence angle prediction, achieving around 80% overall accuracy and per-class accuracy.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".