Deep Learning for Marine Resources Classification in Non-Structured Scenarios: Training vs. Transfer Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper proposes the use of Deep learning for Marine Resources classification (DeepMaRe), especially the classification of fish images captured in non-structured scenarios. Tests conducted using two state of the art deep CNN architectures show that Deep learning can be used efficiently in this type of classifications. AlexNet and GoogLeNet were both used to classify the images captured onboard of fishing boats. The best results were obtained using transfer learning and pretrained models. Using this strategy, AlexNet and GoogLeNet achieve respectively a success rate of 94.01% and 96.01%. These results are further improved by extracting and using fish areas for training and classification. The accuracy of cropped fish areas classification obtained 96.35% with AlexNet and 96.54% with GoogLeNet. Also, the top-2 accuracy obtained by GoogLeNet was equal to 97.87% for the full image classification and 98.94% for the cropped images.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it