AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation
Bibliographic record
Abstract
Improving neural network performance often requires significant computational resources and architectural modifications. We propose AdCorDA (Adversarial Correction and Domain Adaptation), a lightweight yet effective two-stage method that improves model accuracy with minimal overhead. In the first stage, adversarial correction identifies misclassified training samples and replaces them with adversarially corrected versions, forming a refined training set. In the second stage, domain adaptation fine-tunes the model by adapting from the corrected training set back to the original one. Extensive experiments demonstrate that AdCorDA improves accuracy by over 5% on CIFAR, 1% on CINIC-10, and 1-2% on small subsets of ImageNet compared to standard fine-tuning. Our approach does not heavily rely on the neural network architecture and datasets, improving models' performances in most cases within just a few training epochs. Furthermore, it enhances robustness against adversarial attacks, making it a practical and effective refinement technique.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 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".