Defence against Image Distortions using Artificial Immune Systems
Bibliographic record
Abstract
We study object detection and image classification models and observe that their respective architectures are vulnerable to image distortions such as noise, compression, blur or snow. We propose alleviating this problem by training the models with antibodies generated using Artificial Immune Systems (AIS) from original training samples (antigens). These antibodies are AIS-distorted antigens at the pixel level through cycles of “select, clone, mutate, select” until an affinity to the antigen is achieved. We then add the antibodies to the antigens, train the models, validate and test them under 15 distortions, and show that our data augmentation approach (AISbod) significantly improved their accuracy without altering their architecture or inference speed. For example, YOLOv4 improves by 3.90% on average over all 15 distortions, 4.06% under snow, and 28.11% under impulse noise. Our simulations show that compared to related defence methods, our method performs better under distortions, is more consistent across datasets and object detection models, and also under clean samples. Moreover, we show that our approach to image classification significantly improves accuracy under distortions.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".