Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation

Abstract Heterogeneous domain adaptation (HDA) aims to leverage knowledge from a source domain for helping learn an accurate model in a heterogeneous target domain. HDA is exceedingly challenging since the feature spaces of domains are distinct. To tackle this issue, we propose a unified learning framework called Discriminative Distribution Alignment (DDA) for deriving a domain-invariant subspace. The proposed DDA can simultaneously match the discriminative directions of domains, align the distributions across domains, and enhance the separability of data during adaptation. To achieve this, DDA trains an adaptive classifier by both reducing the distribution divergence and enlarging distances between class centroids. Based on the proposed DDA framework, we further develop two methods, by embedding the cross-entropy loss and squared loss into this framework, respectively. We conduct experiments on the tasks of categorization across domains and modalities. Experimental results clearly demonstrate that the proposed DDA outperforms several state-of-the-art models.

[1]  Ivor W. Tsang,et al.  Heterogeneous Domain Adaptation for Multiple Classes , 2014, AISTATS.

[2]  Yong Luo,et al.  Transferring Knowledge Fragments for Learning Distance Metric from a Heterogeneous Domain , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Chang Wang,et al.  Heterogeneous Domain Adaptation Using Manifold Alignment , 2011, IJCAI.

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

[5]  Jing Zhang,et al.  Joint Geometrical and Statistical Alignment for Visual Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Pong C. Yuen,et al.  Learning domain-shared group-sparse representation for unsupervised domain adaptation , 2018, Pattern Recognit..

[7]  Wen Li,et al.  Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation , 2018, IJCAI.

[8]  Philip S. Yu,et al.  Visual Domain Adaptation with Manifold Embedded Distribution Alignment , 2018, ACM Multimedia.

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

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

[11]  Massih-Reza Amini,et al.  Learning from Multiple Partially Observed Views - an Application to Multilingual Text Categorization , 2009, NIPS.

[12]  Jorge Nocedal,et al.  On the limited memory BFGS method for large scale optimization , 1989, Math. Program..

[13]  Taghi M. Khoshgoftaar,et al.  A survey on heterogeneous transfer learning , 2017, Journal of Big Data.

[14]  Ivor W. Tsang,et al.  Learning with Augmented Features for Heterogeneous Domain Adaptation , 2012, ICML.

[15]  Min Xiao,et al.  Semi-supervised Subspace Co-Projection for Multi-class Heterogeneous Domain Adaptation , 2015, ECML/PKDD.

[16]  Trevor Darrell,et al.  Efficient Learning of Domain-invariant Image Representations , 2013, ICLR.

[17]  George Trigeorgis,et al.  Domain Separation Networks , 2016, NIPS.

[18]  Chong-Wah Ngo,et al.  Semi-supervised Domain Adaptation with Subspace Learning for visual recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[20]  Min Xiao,et al.  Feature Space Independent Semi-Supervised Domain Adaptation via Kernel Matching , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Yu-Chiang Frank Wang,et al.  Heterogeneous domain adaptation with label and structure consistency , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Ming-Syan Chen,et al.  Transfer Neural Trees for Heterogeneous Domain Adaptation , 2016, ECCV.

[23]  Yi-Ting Chiang,et al.  A discriminative feature mapping approach to heterogeneous domain adaptation , 2018, Pattern Recognit. Lett..

[24]  Philip S. Yu,et al.  Transfer Learning on Heterogenous Feature Spaces via Spectral Transformation , 2010, 2010 IEEE International Conference on Data Mining.

[25]  De-Chuan Zhan,et al.  Distance Metric Facilitated Transportation between Heterogeneous Domains , 2018, IJCAI.

[26]  Yu-Chiang Frank Wang,et al.  Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[28]  Qiang Yang,et al.  Transitive Transfer Learning , 2015, KDD.

[29]  Yu-Chiang Frank Wang,et al.  Recognizing heterogeneous cross-domain data via generalized joint distribution adaptation , 2016, 2016 IEEE International Conference on Multimedia and Expo (ICME).

[30]  Michael K. Ng,et al.  Learning Discriminative Correlation Subspace for Heterogeneous Domain Adaptation , 2017, IJCAI.

[31]  Alex C. Kot,et al.  Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding , 2019, AAAI.

[32]  Quoc V. Le,et al.  On optimization methods for deep learning , 2011, ICML.

[33]  Ke Lu,et al.  Locality Preserving Joint Transfer for Domain Adaptation , 2019, IEEE Transactions on Image Processing.

[34]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[35]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[36]  Jinhui Tang,et al.  Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation , 2015, ACM Multimedia.

[37]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[38]  Taghi M. Khoshgoftaar,et al.  A survey of transfer learning , 2016, Journal of Big Data.

[39]  Ricardo da Silva Torres,et al.  Semi-supervised transfer subspace for domain adaptation , 2018, Pattern Recognit..

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

[41]  Jiaying Liu,et al.  Adaptive Batch Normalization for practical domain adaptation , 2018, Pattern Recognit..

[42]  Kate Saenko,et al.  Asymmetric and Category Invariant Feature Transformations for Domain Adaptation , 2014, International Journal of Computer Vision.

[43]  Trevor Darrell,et al.  What you saw is not what you get: Domain adaptation using asymmetric kernel transforms , 2011, CVPR 2011.

[44]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Classification , 2011, AAAI.

[45]  Ivor W. Tsang,et al.  Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  Yun Fu,et al.  Semi-supervised Deep Domain Adaptation via Coupled Neural Networks , 2018, IEEE Transactions on Image Processing.

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

[48]  Laurens van der Maaten,et al.  Accelerating t-SNE using tree-based algorithms , 2014, J. Mach. Learn. Res..

[49]  J. Nocedal.  Updating Quasi-Newton Matrices With Limited Storage , 1980 .

[50]  Yue Cao,et al.  Transferable Representation Learning with Deep Adaptation Networks , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Qiang Yang,et al.  Distant Domain Transfer Learning , 2017, AAAI.

[52]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[53]  Philip S. Yu,et al.  Adaptation Regularization: A General Framework for Transfer Learning , 2014, IEEE Transactions on Knowledge and Data Engineering.

[54]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.