Abstract & Overview
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.