IEEE Trans Cybern. 2021 Jul;51(7):3390-3403. doi: 10.1109/TCYB.2020.2974106. Epub 2021 Jun 23.
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.
域自适应适用于将从一个域中学到的知识转移到另一个不同但相关的域。考虑到域之间存在很大的差异，学习更通用的特征表示对于域自适应至关重要。基于此，我们提出了一种自适应组件嵌入（ACE）方法，用于域自适应。具体来说，ACE 学习跨域的自适应组件，将数据嵌入到共享的域不变子空间中，在该子空间中同时对齐一阶统计量和保留几何特性。此外，还对齐域分布的二阶统计量，以进一步减轻域偏移。然后，通过在再生核希尔伯特空间（RKHS）中优化结构风险函数来对对齐的特征表示进行分类。大量实验表明，我们的方法可以在六个域自适应基准上很好地工作，验证了 ACE 的有效性。
