A Salient Feature-guided Network Using a Two-stage Transfer Learning Strategy for Few-Shot Aircraft Detection in SAR Images
Bibliographic record
Abstract
Deep learning methods have shown promising potential in target detection, which typically require large amounts of annotated data. However, it is challenging to obtain substantial volumes of Synthetic Aperture Radar (SAR) images due to high acquisition costs and time-consuming annotation processes. Moreover, aircrafts in SAR images are often discrete and variable, while the complex scattering mechanisms between targets and background further complicate detection. High-precision target detection with sparse training samples has become one of the bottlenecks that restricts the improvement of detection performance. In this paper, a Salient Feature-guided Network using a two-stage Transfer Learning strategy (SFN-TL) is proposed for few-shot aircraft detection in SAR images. Especially, a Salient Feature Enhancement Module (SFEM) is proposed to improve feature extraction ability with sparse training samples, which is composed of an auxiliary branch using a generator network. Additionally, the issue of sparse target feature representation in SAR images is addressed by introducing a Context-aware Feature Fusion Module (CFFM). Experiments conducted on the SAR-AIRcraft-1.0 dataset demonstrate the effectiveness of the proposed method. The proposed method has achieved a novel class Average Precision (nAP) of 20.2%, 40.1%, and 66.4% with 5, 10, and 30 training images per novel class, respectively.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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".