A Novel Domain Adaptation-based Framework for Face Recognition Under Darkened and Overexposed Situations
Bibliographic record
Abstract
Face recognition has become a cornerstone technology in various domains, including security, healthcare, and personalized applications. While traditional methods relied on handcrafted features and classical machine learning, advancements in deep learning have significantly improved face recognition's accuracy and robustness. However, challenges such as environmental variations—darkened or overexposed images—create domain shifts that compromise the generalization of these models. To address this, domain adaptation techniques have emerged as a promising solution, aligning feature distributions between source domain and target domain. This paper proposes a domain adaptation framework integrating Correlation Alignment (CORAL) and a Residual Network (ResNet) to enhance model robustness under varying conditions. Our method effectively reduces domain discrepancies using CORAL loss. Experimental results demonstrate that domain adaptation significantly improves model performance, as evidenced by reduced Equal Error Rates (EER) and enhanced feature alignment in challenging lighting scenarios. Despite its success, domain adaptation faces challenges such as computational costs and handling extreme distortions, highlighting the need for further research into more efficient and generalized approaches.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".