期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 51, 期 7, 页码 3390-3403出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2020.2974106
关键词
Geometry; Manifolds; Task analysis; Kernel; Neural networks; Cybernetics; Hilbert space; Distribution alignment; domain adaptation; subspace learning; transfer learning
类别
资金
- National Natural Science Foundation of China [61806039, 61832001]
- Sichuan Department of Science and Technology [2019YFG0141]
The proposed adaptive component embedding (ACE) method learns adaptive components across domains to embed data into a shared domain-invariant subspace for domain adaptation. Extensive experiments show that the method performs well on six domain adaptation benchmarks, confirming the effectiveness of ACE.
Domain adaptation is suitable for transferring knowledge learned from one domain to a different but related domain. Considering the substantially large domain discrepancies, learning a more generalized feature representation is crucial for domain adaptation. On account of this, we propose an adaptive component embedding (ACE) method, for domain adaptation. Specifically, ACE learns adaptive components across domains to embed data into a shared domain-invariant subspace, in which the first-order statistics is aligned and the geometric properties are preserved simultaneously. Furthermore, the second-order statistics of domain distributions is also aligned to further mitigate domain shifts. Then, the aligned feature representation is classified by optimizing the structural risk functional in the reproducing kernel Hilbert space (RKHS). Extensive experiments show that our method can work well on six domain adaptation benchmarks, which verifies the effectiveness of ACE.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据