TarGAN: Generating target data with class labels for unsupervised domain adaptation

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.

Download Full-text

Unsupervised Domain Adaptation for Person Re-Identification with Few and Unlabeled Target Data

Advances in Visual Computing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-64559-5_28 ◽

2020 ◽

pp. 357-373

Author(s):

George Galanakis ◽

Xenophon Zabulis ◽

Antonis A. Argyros

Keyword(s):

Domain Adaptation ◽

Unsupervised Domain Adaptation ◽

Target Data

Download Full-text

Learning Domain Invariant Representation via Self-Rugularization

Journal of the Korea Institute of Military Science and Technology ◽

10.9766/kimst.2021.24.4.382 ◽

2021 ◽

Vol 24 (4) ◽

pp. 382-391

Author(s):

Jaeguk Hyun ◽

ChanYong Lee ◽

Hoseong Kim ◽

Hyunjung Yoo ◽

Eunjin Koh

Keyword(s):

Domain Adaptation ◽

Regularization Methods ◽

Invariant Representation ◽

Large Dataset ◽

Style Transfer ◽

Unsupervised Domain Adaptation ◽

Loss Term ◽

Target Data ◽

Small Dataset ◽

Feature Alignment

Unsupervised domain adaptation often gives impressive solutions to handle domain shift of data. Most of current approaches assume that unlabeled target data to train is abundant. This assumption is not always true in practices. To tackle this issue, we propose a general solution to solve the domain gap minimization problem without any target data. Our method consists of two regularization steps. The first step is a pixel regularization by arbitrary style transfer. Recently, some methods bring style transfer algorithms to domain adaptation and domain generalization process. They use style transfer algorithms to remove texture bias in source domain data. We also use style transfer algorithms for removing texture bias, but our method depends on neither domain adaptation nor domain generalization paradigm. The second regularization step is a feature regularization by feature alignment. Adding a feature alignment loss term to the model loss, the model learns domain invariant representation more efficiently. We evaluate our regularization methods from several experiments both on small dataset and large dataset. From the experiments, we show that our model can learn domain invariant representation as much as unsupervised domain adaptation methods.

Download Full-text

Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33014106 ◽

2019 ◽

Vol 33 ◽

pp. 4106-4113 ◽

Cited By ~ 1

Author(s):

Atsutoshi Kumagai ◽

Tomoharu Iwata

Keyword(s):

Domain Adaptation ◽

Feature Space ◽

Classification Performance ◽

Target Domain ◽

Target Feature ◽

Maximum Mean Discrepancy ◽

Source Domain ◽

Unsupervised Domain Adaptation ◽

Real World Datasets ◽

Target Data

We propose a simple yet effective method for unsupervised domain adaptation. When training and test distributions are different, standard supervised learning methods perform poorly. Semi-supervised domain adaptation methods have been developed for the case where labeled data in the target domain are available. However, the target data are often unlabeled in practice. Therefore, unsupervised domain adaptation, which does not require labels for target data, is receiving a lot of attention. The proposed method minimizes the discrepancy between the source and target distributions of input features by transforming the feature space of the source domain. Since such unilateral transformations transfer knowledge in the source domain to the target one without reducing dimensionality, the proposed method can effectively perform domain adaptation without losing information to be transfered. With the proposed method, it is assumed that the transformed features and the original features differ by a small residual to preserve the relationship between features and labels. This transformation is learned by aligning the higher-order moments of the source and target feature distributions based on the maximum mean discrepancy, which enables to compare two distributions without density estimation. Once the transformation is found, we learn supervised models by using the transformed source data and their labels. We use two real-world datasets to demonstrate experimentally that the proposed method achieves better classification performance than existing methods for unsupervised domain adaptation.

Download Full-text

Improving Domain-Specific Classification by Collaborative Learning with Adaptation Networks

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015450 ◽

2019 ◽

Vol 33 ◽

pp. 5450-5457 ◽

Cited By ~ 1

Author(s):

Si Wu ◽

Jian Zhong ◽

Wenming Cao ◽

Rui Li ◽

Zhiwen Yu ◽

...

Keyword(s):

Domain Adaptation ◽

Visual Adaptation ◽

Generalization Capability ◽

Target Domain ◽

Domain Specific ◽

Unsupervised Domain Adaptation ◽

Source Data ◽

Data Points ◽

Invariant Representations ◽

Target Data

For unsupervised domain adaptation, the process of learning domain-invariant representations could be dominated by the labeled source data, such that the specific characteristics of the target domain may be ignored. In order to improve the performance in inferring target labels, we propose a targetspecific network which is capable of learning collaboratively with a domain adaptation network, instead of directly minimizing domain discrepancy. A clustering regularization is also utilized to improve the generalization capability of the target-specific network by forcing target data points to be close to accumulated class centers. As this network learns and specializes to the target domain, its performance in inferring target labels improves, which in turn facilitates the learning process of the adaptation network. Therefore, there is a mutually beneficial relationship between these two networks. We perform extensive experiments on multiple digit and object datasets, and the effectiveness and superiority of the proposed approach is presented and verified on multiple visual adaptation benchmarks, e.g., we improve the state-ofthe-art on the task of MNIST→SVHN from 76.5% to 84.9% without specific augmentation.

Download Full-text