Few Shot Learning of COVID-19 Classification Based on Sequential and Pretrained Models: A Thick Data Approach
Bibliographic record
Abstract
Classification tasks face several issues when applied to complex data sets and sophisticated images such as CT scans. Long training times are needed to properly train traditional networks to classify images, as well as the need for large amounts of data for these networks to draw accurate conclusions. Even when supplied with large datasets, popular neural networks like VGG and ResNet fail to classify images accurately and consistently for sensitive tasks like identifying COVID-19 in a CT lung scan. To overcome these challenges, we apply Siamese neural network architecture, which has been reported to reduce training times and required training data, to a sequential network. To further empower this network, we incorporate thick data heuristics into the CT image dataset, specifically, we annotate areas of interest in the images that a radiologist would be looking for to make a diagnosis, such as ground glass opacities. Our network outperforms five leading image classification neural networks by about 3% when classifying the same CT lung scan images as positive or negative for COVID-19. By applying data thickening heuristics, we have shown that accuracy is improved, and suspect that the accuracy will continue to increase as more heuristics based on more radiologists and imaging experts are to be added on top of what we have considered in this paper.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.003 |
| 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".