Enhanced Image Classification Using Modified Dense Convolutional Network (MDCN) Utilizing Transfer Learning and Optimization Algorithms
Bibliographic record
Abstract
Classification of image is a crucial part in computer vision, but current approaches often struggle with challenges such as high computational cost, difficulty in handling small datasets, and sensitivity to noisy data. Traditional and modern deep-learning models need careful adjustment of hyperparameters like batch-size and learningrate, which is a time-consuming manual process that increases training time. To solve these problems, this study introduces a deep-learning framework which integrates Transfer-learning (Feature-Extraction & Knowledge-Distillation) with optimization techniques to enhance accuracy and efficiency. First, a pre-trained ResNet50 architecture is fine-tuned on the Animal Classification dataset, which contains four different animal classes. The learned weights from ResNet50, obtained through feature-extraction and knowledge-distillation, are then transferred to the Modified Dense Convolutional Network (MDCN) to enhance its ability to extract meaningful features and improve classification performance. To further optimize the model, the Whale Optimization Algorithm (WOA) is used for automatic hyperparameter tuning. Instead of manually adjusting parameters like batch-size and learning-rate, WOA selects the best values, reducing training time and improving overall accuracy. Results from experimental-simulations suggest that the proposed method achieves 99.45 % accuracy in 40 epochs, outperforming the benchmark algorithms such as proposed algorithm with Grid Search, proposed algorithm without WOA, Dense-Net 121, Resnet50 and Long Short-Term Memory (LSTM). The combination of transfer-learning and optimization helps speed up training while reducing errors.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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 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".