AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning

• DOI: 10.48550/arxiv.2405.09582
• Publication Date: 2024-05-14
• Authors: Zhuoying Li; Bohua Wan; Cong Mu; Ruzhang Zhao; Shushan Qiu; Chao Yan
• Keywords: Domain Adaptation

Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, novel approach that combines adversarial training with source-target domain alignment enhance generalization capabilities. By pretraining Coral loss standard loss, AD-Aligning aligns target statistics those of the pretrained encoder, preserving robustness while accommodating shifts. Through extensive experiments on datasets shift scenarios, including noise-induced shifts tasks, demonstrate AD-Aligning's superior performance compared existing methods such as Deep ADDA. Our findings highlight ability emulate nuanced processes inherent human perception, making it promising solution real-world applications requiring adaptable robust strategies.