- Keywords: Deep Learning, Unsupervised Domain Adaptation, Distribution Modeling
- TL;DR: We propose to explicitly model deep feature distributions of source and target data as Gaussian mixture distributions for Unsupervised Domain Adaptation (UDA) and achieve superior results in multiple UDA tasks than state-of-the-art methods.
- Abstract: State-of-the-art Unsupervised Domain Adaptation (UDA) methods learn transferable features by minimizing the feature distribution discrepancy between the source and target domains. Different from these methods which do not model the feature distributions explicitly, in this paper, we explore explicit feature distribution modeling for UDA. In particular, we propose Distribution Matching Prototypical Network (DMPN) to model the deep features from each domain as Gaussian mixture distributions. With explicit feature distribution modeling, we can easily measure the discrepancy between the two domains. In DMPN, we propose two new domain discrepancy losses with probabilistic interpretations. The first one minimizes the distances between the corresponding Gaussian component means of the source and target data. The second one minimizes the pseudo negative log likelihood of generating the target features from source feature distribution. To learn both discriminative and domain invariant features, DMPN is trained by minimizing the classification loss on the labeled source data and the domain discrepancy losses together. Extensive experiments are conducted over two UDA tasks. Our approach yields a large margin in the Digits Image transfer task over state-of-the-art approaches. More remarkably, DMPN obtains a mean accuracy of 81.4% on VisDA 2017 dataset. The hyper-parameter sensitivity analysis shows that our approach is robust w.r.t hyper-parameter changes.
- Original Pdf: pdf