Transfer Learning and Fine Tuning in Modified VGG for Haploid Diploid Corn Seed Images Classification
Bibliographic record
Abstract
Seeds play an essential role in corn cultivation.Seed is one of the determining factors for plants to grow well.Corn seeds generally are diploid, with two chromosomes in one set.Besides diploid, there are haploid seeds that only have one chromosome.The haploid is only 0.1% of the total natural corn seed.Engineering technology development produced double haploid (DH).Corn seed yields can genetically improve plants.DH can shorten the period and improve breeding efficiency.In this article, we classify the image of corn seeds-public data from a rovile dataset with 1,230 haploid and 1,770 diploid images.The research steps included pre-processing, resizing, and undersampling the majority class for balanced data.Then, split 80% training and 20% testing data.The training data uses 5-fold cross-validation.Classification using a Convolutional Neural Network (CNN) with modified VGG architecture was made by adding two dropout layers 0.5 after the dense layer.The CNN architecture also uses transfer learning and fine-tuning techniques.Transfer learning improves performance, minimizes computing, and reduces training time.Fine tuning aims to taking a model that has been trained on a specific task and then piecing together the last few layers of that model to solve a new task.The model from the crossvalidation results is then used for data testing.The test results show that the performance for accuracy, precision, recall, f1-score, and AUC is 96.83%, 95.9%, 98.87%, 97.36%, and 96.39%, 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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".