Structured serialization semantic transfer network for unsupervised cross-domain and retrieval

INFORMATION PROCESSING & MANAGEMENT(2024)

引用 0|浏览34
暂无评分
摘要
Unsupervised domain adaptation aims to apply a model trained from labeled datasets to unlabeled datasets, which still exist challenges to minimize the degree of inter-domain sam-ple differences. In the paper, we design the structured serialization semantic transfer net-work (S3TN) to further minimize the domain gap by structured and serialization information at the semantic level. Our S3TN contains the spatially structured alignment module (SSA) and the category serialization alignment module (CSA). The spatially structured alignment module preserves the structured information between different category-level centers (spatial associations between different categories in the feature space of category-level centers), further aligning the structured correlations between different domains. The serialization alignment module enhances the reliability of the category-level centers by avoiding valid information loss and error information retention, which further mitigates the problem of knowledge forgetting. Various experiments have been conducted on three widely-used datasets, Office-31, MI3DOR-1, and MI3DOR-2, and the experimental results verify the effectiveness of our proposed method. Especially on Office-31 dataset, our method outperforms the existing methods with gains of 1.3% for the average of the classification accuracy.
更多
查看译文
关键词
Unsupervised domain adaptation,Cross-domain alignment,Structured information,Category serialization information
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要