论文标题
Fisher深区适应
Fisher Deep Domain Adaptation
论文作者
论文摘要
深区适应模型通过利用标记的源域的知识来学习未标记的目标域中的神经网络。这可以通过学习域不变的特征空间来实现。尽管学习的表示形式在源域中是可分离的，但它们通常具有较大的差异，并且具有不同类标签的样品往往在目标域中重叠，这会产生次优的适应性性能。为了填补空白，提出了一个渔民的损失，以学习歧视性表示，这些表示是紧凑且可分开的阶层之间。两个基准数据集的实验结果表明，Fisher损失是深层域适应性的一般有效损失。当将其与广泛采用的转移标准（包括MMD，珊瑚和域对抗损失）一起使用时，会带来明显的改进。例如，当将Fisher损失与办公室家庭数据集中的域对抗损失一起使用时，就可以达到平均准确性的6.67％的绝对提高。
Deep domain adaptation models learn a neural network in an unlabeled target domain by leveraging the knowledge from a labeled source domain. This can be achieved by learning a domain-invariant feature space. Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance. To fill the gap, a Fisher loss is proposed to learn discriminative representations which are within-class compact and between-class separable. Experimental results on two benchmark datasets show that the Fisher loss is a general and effective loss for deep domain adaptation. Noticeable improvements are brought when it is used together with widely adopted transfer criteria, including MMD, CORAL and domain adversarial loss. For example, an absolute improvement of 6.67% in terms of the mean accuracy is attained when the Fisher loss is used together with the domain adversarial loss on the Office-Home dataset.
