A Novel Deep Learning-Based Compressed Image Enhancement Method for Machine Consumption
Bibliographic record
Abstract
Image compression reduces storage, and transmission demands but often degrades image quality, introducing artifacts such as blurring and blocking. While deep learning-based methods have shown remarkable progress in the enhancement of compressed images, most of these approaches are designed with human perception in mind, focusing on improving subjective visual quality. As the field of artificial intelligence continues to evolve, the consumption of images by machines, rather than humans, has become increasingly relevant. Compressed images, when fed into machine learning models, can cause significant performance degradation due to distortions introduced during compression. To address this gap, we propose a joint restoration-classification network specifically designed to enhance compressed images for machine consumption. Our approach combines an image enhancement network with an image classification network, using a linear combination of Charbonnier and cross-entropy loss terms to optimize classification accuracy while balancing restoration metrics such as PSNR and SSIM. Our experiments show that our approach increases top-1 classification accuracy by 6.2% for JPEG compressed images at quality level 40 and by 12.2% for images at quality level 10, compared to the baseline performance on the same compressed images without enhancement.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".