Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.09582 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909381538349056 |
|---|---|
| author | Li, Zhuoying Wan, Bohua Mu, Cong Zhao, Ruzhang Qiu, Shushan Yan, Chao |
| author_facet | Li, Zhuoying Wan, Bohua Mu, Cong Zhao, Ruzhang Qiu, Shushan Yan, Chao |
| contents | 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, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Aligning aligns target domain statistics with those of the pretrained encoder, preserving robustness while accommodating domain shifts. Through extensive experiments on diverse datasets and domain shift scenarios, including noise-induced shifts and cognitive domain adaptation tasks, we demonstrate AD-Aligning's superior performance compared to existing methods such as Deep Coral and ADDA. Our findings highlight AD-Aligning's ability to emulate the nuanced cognitive processes inherent in human perception, making it a promising solution for real-world applications requiring adaptable and robust domain adaptation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09582 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning Li, Zhuoying Wan, Bohua Mu, Cong Zhao, Ruzhang Qiu, Shushan Yan, Chao Computer Vision and Pattern Recognition Image and Video Processing 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, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Aligning aligns target domain statistics with those of the pretrained encoder, preserving robustness while accommodating domain shifts. Through extensive experiments on diverse datasets and domain shift scenarios, including noise-induced shifts and cognitive domain adaptation tasks, we demonstrate AD-Aligning's superior performance compared to existing methods such as Deep Coral and ADDA. Our findings highlight AD-Aligning's ability to emulate the nuanced cognitive processes inherent in human perception, making it a promising solution for real-world applications requiring adaptable and robust domain adaptation strategies. |
| title | AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2405.09582 |