.png){kind=icon}
返回
Dynamic prototype-guided structural information maintaining for unsupervised domain adaptation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10044-025-01435-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised Domain Adaptation (UDA) intends to transfer the knowledge learned from labeled source domain to unlabeled target domain. Most existing methods employ domain adversarial training to align the feature space distributions of two domains. However, these methods may destroy the discriminative structural information. In this paper, we propose a Dynamic Prototype-guided Structural Information Maintaining (DPSIM) approach to preserve the structural information of the target domain based on pairwise semantic similarity. Specifically, we propose a dynamic prototype learning module to learn the categorical intrinsic representation of the source domain and then to predict the similarity of pairwise samples of the target domain. Finally, a structural information maintaining module is proposed to restrict the target domain by discriminating structural information. Extensive experiments on both image classification and object detection tasks demonstrate the effectiveness of our method.
Keyword:
Unsupervised domain adaptation
Prototype learning
Structural information
Pairwise similarity
期刊
IF:
2
论文数:
2.0K
被引数:
1.9K
机构
引用论文
.png){kind=icon}
Domain adaption based on source dictionary regularized RKHS subspace learning基于源字典正则化RKHS子空间学习的域自适应
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容