School of Computer Science and Engineering, University of Electronic Science and Technology of China, China.
School of Computer Science and Engineering, University of Electronic Science and Technology of China, China.
Neural Netw. 2020 Oct;130:39-48. doi: 10.1016/j.neunet.2020.06.016. Epub 2020 Jun 25.
Domain adaptation tackles the problem where the training source domain and the test target domain have distinctive data distributions, and therefore improves the generalization ability of deep models. The very popular mechanism of domain adaptation is to learn a new feature representation which is supposed to be domain-invariant, so that the classifiers trained on the source domain can be directly applied to the target domain. However, recent work reveals that learning new feature representations may potentially deteriorate the adaptability of the original features and increase the expected error bound of the target domain. To address this, we propose to adapt classifiers rather than features. Specifically, we fill in the distribution gaps between domains by some additional transferable representations which are explicitly learned from the original features while keeping the original features unchanged. In addition, we argue that transferable representations should be able to be translated from one domain to the other with appropriate mappings. At the same time, we introduce conditional entropy to mitigate the semantic confusion during mapping. Experiments on both standard and large-scale datasets verify that our method is able to achieve the new state-of-the-art results on unsupervised domain adaptation.
域自适应解决了训练源域和测试目标域具有不同数据分布的问题，从而提高了深度学习模型的泛化能力。非常流行的域自适应机制是学习新的特征表示，该表示应该是域不变的，以便在源域上训练的分类器可以直接应用于目标域。然而，最近的工作表明，学习新的特征表示可能会潜在地恶化原始特征的适应性，并增加目标域的期望误差边界。为了解决这个问题，我们建议适应分类器而不是特征。具体来说，我们通过一些额外的可转移表示来填补域之间的分布差距，这些可转移表示是从原始特征中明确学习的，同时保持原始特征不变。此外，我们认为可转移的表示应该能够通过适当的映射从一个域转换到另一个域。同时，我们引入条件熵来减轻映射过程中的语义混淆。在标准和大规模数据集上的实验验证了我们的方法能够在无监督域自适应中达到新的最先进的结果。
