Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

by   Hui Tang, et al.

Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution shifts from the target one. Mainstream UDA methods learn aligned features between the two domains, such that a classifier trained on the source features can be readily applied to the target ones. However, such a transferring strategy has a potential risk of damaging the intrinsic discrimination of target data. To alleviate this risk, we are motivated by the assumption of structural domain similarity, and propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data. We constrain the clustering solutions using structural source regularization that hinges on our assumed structural domain similarity. Technically, we use a flexible framework of deep network based discriminative clustering that minimizes the KL divergence between predictive label distribution of the network and an introduced auxiliary one; replacing the auxiliary distribution with that formed by ground-truth labels of source data implements the structural source regularization via a simple strategy of joint network training. We term our proposed method as Structurally Regularized Deep Clustering (SRDC), where we also enhance target discrimination with clustering of intermediate network features, and enhance structural regularization with soft selection of less divergent source examples. Careful ablation studies show the efficacy of our proposed SRDC. Notably, with no explicit domain alignment, SRDC outperforms all existing methods on three UDA benchmarks.


page 6

page 7


Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering

Unsupervised domain adaptation (UDA) is to learn classification models t...

Unsupervised Domain Adaptation via Distilled Discriminative Clustering

Unsupervised domain adaptation addresses the problem of classifying data...

Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation

Source-Free Domain Adaptation (SFDA) aims to solve the domain adaptation...

Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding

Recent studies have shown that pseudo labels can contribute to unsupervi...

Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

In unsupervised domain adaptation (UDA), classifiers for the target doma...

Deep clustering: On the link between discriminative models and K-means

In the context of recent deep clustering studies, discriminative models ...

Please sign up or login with your details

Forgot password? Click here to reset