MiNet: Efficient Deep Learning Automatic Target Recognition for Small Autonomous Vehicles
Bibliographic record
Abstract
On-the-fly automatic target recognition (ATR) is a challenge for small autonomous vehicles performing remote sensing. Advances in deep learning have made object detection practicable on data from a variety of sensor types, and neural network-based object detector models trained on big data sets of natural images are commonly adapted to the remote sensor (RS) domain via transfer learning. However, constraints of small vehicle hardware, such as computational performance and battery power, limit capacity for running deep learning models onboard. Standard pretrained object detection models, such as YOLO and R-CNN, contain large convolutional neural networks requiring tens to hundreds of billions of floating-point operations to distinguish between many natural image object classes. Such large models may be overly complex for ATR tasks in RS data. This letter describes an efficient deep learning model, MiNet, developed to detect mine-like objects in sonar data. It was built in Keras and TensorFlow and trained entirely on real and synthetically generated sonar data using an incremental training procedure. MiNet was successfully deployed onboard small OceanServer Iver3 autonomous underwater vehicles during the REBOOT sea trial and predicted the latitude, longitude, and class of objects detected in sonar images within minutes of the completion of each mission leg.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".