Domain adaptation has become a resounding success in learning a domain agnostic model that performs well on target dataset by leveraging source dataset which has related data distribution. Most of existing works aim at learning domain-invariant features across different domains, but they ignore the discriminability of learned features although it is import to improve the model's performance. This paper proposes a novel adversarial sliced Wasserstein domain adaptation network (AWDAN) that uses a shared encoder and classifier along with a domain classifier to enhance the discriminability of the domain-invariant features. AWDAN utilizes adversarial learning to learn domain-invariant features in feature space and simultaneously minimizes sliced Wasserstein distance in label space to enforce the generated features to be discriminative that guarantees the transfer performance. Meanwhile, we propose to fix the weights of the pre-trained CNN backbone to guarantee its adaptability. We provide theoretical analysis to demonstrate the efficacy of AWDAN. Experimental results show that the proposed AWDAN significantly outperforms existing domain adaptation methods on three visual domain adaptation tasks. Feature visualizations verify that AWDAN learns both domain-invariant and discriminative features, and can achieve domain agnostic feature learning.

在利用域相关模型通过利用具有相关数据分布的源数据集来学习对目标数据集表现良好的域不可知模型方面，域适应已取得了巨大的成功。现有的大多数工作都旨在学习跨不同领域的领域不变特征，但是尽管它是提高模型性能的重要手段，但他们忽略了学习特征的可分辨性。本文提出了一种新颖的对抗式切片Wasserstein域自适应网络（AWDAN），该网络使用共享的编码器和分类器以及域分类器来增强域不变特征的可分辨性。AWDAN利用对抗学习来学习特征空间中的领域不变特征，同时最小化标签空间中的切片Wasserstein距离，以强制生成的特征具有判别力，从而保证了传输性能。同时，我们建议固定预训练的CNN骨干权重以确保其适应性。我们提供理论分析以证明AWDAN的功效。实验结果表明，提出的AWDAN在三个视觉域自适应任务上明显优于现有的域自适应方法。特征可视化可以验证AWDAN是否学习域不变和区分特征，并且可以实现域不可知特征学习。我们建议固定预训练的CNN骨干权重，以确保其适应性。我们提供理论分析以证明AWDAN的功效。实验结果表明，提出的AWDAN在三个视觉域自适应任务上明显优于现有的域自适应方法。特征可视化可以验证AWDAN是否学习域不变和区分特征，并且可以实现域不可知特征学习。我们建议固定预训练的CNN骨干的权重，以确保其适应性。我们提供理论分析以证明AWDAN的功效。实验结果表明，提出的AWDAN在三个视觉域自适应任务上明显优于现有的域自适应方法。特征可视化可以验证AWDAN是否学习域不变和区分特征，并且可以实现域不可知特征学习。