IEEE Trans Cybern. 2022 Apr;52(4):2618-2629. doi: 10.1109/TCYB.2020.3004398. Epub 2022 Apr 5.
In general, existing cross-domain recognition methods mainly focus on changing the feature representation of data or modifying the classifier parameter and their efficiencies are indicated by the better performance. However, most existing methods do not simultaneously integrate them into a unified optimization objective for further improving the learning efficiency. In this article, we propose a novel cross-domain recognition algorithm framework by integrating both of them. Specifically, we reduce the discrepancies in both the conditional distribution and marginal distribution between different domains in order to learn a new feature representation which pulls the data from different domains closer on the whole. However, the data from different domains but the same class cannot interlace together enough and thus it is not reasonable to mix them for training a single classifier. To this end, we further propose to learn double classifiers on the respective domain and require that they dynamically approximate to each other during learning. This guarantees that we finally learn a suitable classifier from the double classifiers by using the strategy of classifier fusion. The experiments show that the proposed method outperforms over the state-of-the-art methods.
一般来说，现有的跨域识别方法主要侧重于改变数据的特征表示或修改分类器参数，其效率通过更好的性能来体现。然而，大多数现有的方法并没有将它们同时集成到一个统一的优化目标中，以进一步提高学习效率。在本文中，我们通过整合这两个方面，提出了一种新的跨域识别算法框架。具体来说，我们减少了不同域之间条件分布和边缘分布的差异，以便学习新的特征表示，从而使不同域的数据在整体上更加接近。然而，来自不同域但属于同一类别的数据不能充分交织在一起，因此将它们混合在一起训练单个分类器是不合理的。为此，我们进一步提出在各自的域上学习双分类器，并要求它们在学习过程中动态地相互逼近。这保证了我们最终通过分类器融合策略从双分类器中学习到合适的分类器。实验表明，所提出的方法优于现有的最先进的方法。
