Research on the classification of the paintings of 10 impressionist painters through deep learning
Bibliographic record
Abstract
Since professional Go players Lee Sedol and Jie Ke were beaten by AlphaGo which was developed by Google’s sister company Deepmind, the artificial technology be- hinds it, deep learning (DL), has been drawn attention to people all over the world. Although the goal of this research is just to simply classify paintings of 10 impressionists, by using a convolutional neural network (CNN), there is something interesting found during the research to suggest that how powerful deep learning is. For the author himself, he cannot do that and even his friends who learning impressionists. The dataset is acquired from the Kaggle (Impressionist_Classifier_Data), which helps for this research to classify Impressionist painters into 10 categories including Camille Pisarro, Childe Hassam, Claude Monet, Edgar Degas, Henri Matisse, John Singer- Sargent, Paul Cezanne, Paul Gauguin, Pierre-Auguste Renoir, Vincent van Gogh. This research starts with introducing convolutional neural networks (CNNs) including convolutional layer, filters, pooling layer, fully connected layer. Then, based on the test result of the classifier, the author shows accuracy, loss graphof the training session, accuracy, precision, recall, macro f1-score, confusion matrix and unexpected findings of the classifier. The accuracy of the classifier is around 95 percent in training, 60 percent in validation and 83 percent in testing. The author found that even though he changed color of the test painting and transfer the style of painting, the classifier can still predict correctly.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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) | 0.002 | 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".