Dual Alignment for Partial Domain Adaptation

Partial domain adaptation (PDA) aims to transfer knowledge from a label-rich source domain to a label-scarce target domain based on an assumption that the source label space subsumes the target label space. The major challenge is to promote positive transfer in the shared label space and circumvent negative transfer caused by the large mismatch across different label spaces. In this article, we propose a dual alignment approach for PDA (DAPDA), including three components: 1) a feature extractor extracts source and target features by the Siamese network; 2) a reweighting network produces ``hard'' labels, class-level weights for source features and ``soft'' labels, instance-level weights for target features; 3) a dual alignment network aligns intra domain and interdomain distributions. Specifically, the intra domain alignment aims to minimize the intraclass variances to enhance the intraclass compactness in both domains, and interdomain alignment attempts to reduce the discrepancies across domains by domain-wise and class-wise adaptations. The negative transfer can be alleviated by down-weighting source features with nonshared labels. The positive transfer can be enhanced by upweighting source features with shared labels. The adaptation can be achieved by minimizing the discrepancies based on class-weighted source data with hard labels and instance-weighed target data with soft labels. The effectiveness of our method has been demonstrated by outperforming state-of-the-art PDA methods on several benchmark datasets.

[1]  Pascal Fua,et al.  Beyond Sharing Weights for Deep Domain Adaptation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Praveen Kumar.S.G.  ENTROPY-BASED SAMPLING APPROACHES FOR MULTI-CLASS IMBALANCED PROBLEMS , 2020 .

[3]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[4]  Haibo He,et al.  SDE: A Novel Clustering Framework Based on Sparsity-Density Entropy , 2018, IEEE Transactions on Knowledge and Data Engineering.

[5]  Bo Tang,et al.  A Generative Model for Sparse Hyperparameter Determination , 2018, IEEE Transactions on Big Data.

[6]  Zhu Lei,et al.  Locality Preserving Joint Transfer for Domain Adaptation , 2019, IEEE Transactions on Image Processing.

[7]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Jianmin Wang,et al.  Learning to Transfer Examples for Partial Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[12]  Jing Zhang,et al.  Importance Weighted Adversarial Nets for Partial Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Jianmin Wang,et al.  Partial Transfer Learning with Selective Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Haibo He,et al.  Adversarial Domain Adaptation via Category Transfer , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[15]  Hong Yan,et al.  Generalized Conditional Domain Adaptation: A Causal Perspective With Low-Rank Translators , 2020, IEEE Transactions on Cybernetics.

[16]  Muhammad Uzair,et al.  Blind Domain Adaptation With Augmented Extreme Learning Machine Features , 2017, IEEE Transactions on Cybernetics.

[17]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[18]  Jianmin Wang,et al.  Partial Adversarial Domain Adaptation , 2018, ECCV.

[19]  Jian Shen,et al.  Wasserstein Distance Guided Representation Learning for Domain Adaptation , 2017, AAAI.

[20]  Ke Lu,et al.  Transfer Independently Together: A Generalized Framework for Domain Adaptation , 2019, IEEE Transactions on Cybernetics.

[21]  Urbano J. Nunes,et al.  Importance Weighted Import Vector Machine for Unsupervised Domain Adaptation , 2017, IEEE Transactions on Cybernetics.

[22]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[23]  Hariharan Narayanan,et al.  Sample Complexity of Testing the Manifold Hypothesis , 2010, NIPS.

[24]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[25]  Michael I. Jordan,et al.  Deep Transfer Learning with Joint Adaptation Networks , 2016, ICML.

[26]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[28]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[29]  Nicolas Courty,et al.  DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation , 2018, ECCV.

[30]  Haibo He,et al.  Model-Free Real-Time EV Charging Scheduling Based on Deep Reinforcement Learning , 2019, IEEE Transactions on Smart Grid.

[31]  Ievgen Redko,et al.  Theoretical Analysis of Domain Adaptation with Optimal Transport , 2016, ECML/PKDD.

[32]  François Laviolette,et al.  Domain-Adversarial Neural Networks , 2014, ArXiv.

[33]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[34]  Michael I. Jordan,et al.  Unsupervised Domain Adaptation with Residual Transfer Networks , 2016, NIPS.

[35]  Jie Li,et al.  EDOS: Entropy Difference-based Oversampling Approach for Imbalanced Learning , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[36]  Ke Lu,et al.  Heterogeneous Domain Adaptation Through Progressive Alignment , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[37]  Haibo He,et al.  AnswerNet: Learning to Answer Questions , 2019, IEEE Transactions on Big Data.

[38]  Nicolas Courty,et al.  Joint distribution optimal transportation for domain adaptation , 2017, NIPS.

[39]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[40]  David Zhang,et al.  Learning Domain-Invariant Subspace Using Domain Features and Independence Maximization , 2016, IEEE Transactions on Cybernetics.

[41]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[43]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[44]  Jianmin Wang,et al.  Unsupervised Domain Adaptation With Distribution Matching Machines , 2018, AAAI.

[45]  Sethuraman Panchanathan,et al.  Deep Hashing Network for Unsupervised Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Yun Fu,et al.  Deep Transfer Low-Rank Coding for Cross-Domain Learning , 2019, IEEE Transactions on Neural Networks and Learning Systems.