Open Set Domain Adaptation by Backpropagation

Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Most of them are proposed for closed-set scenario, where the source and the target domain completely share the class of their samples. However, in practice, a target domain can contain samples of classes that are not shared by the source domain. We call such classes the “unknown class” and algorithms that work well in the open set situation are very practical. However, most existing distribution matching methods for domain adaptation do not work well in this setting because unknown target samples should not be aligned with the source. In this paper, we propose a method for an open set domain adaptation scenario, which utilizes adversarial training. This approach allows to extract features that separate unknown target from known target samples. During training, we assign two options to the feature generator: aligning target samples with source known ones or rejecting them as unknown target ones. Our method was extensively evaluated and outperformed other methods with a large margin in most settings.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Rahil Garnavi,et al.  Generative OpenMax for Multi-Class Open Set Classification , 2017, BMVC.

[3]  Tatsuya Harada,et al.  Asymmetric Tri-training for Unsupervised Domain Adaptation , 2017, ICML.

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

[5]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[6]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

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

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

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

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

[11]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

[12]  Terrance E. Boult,et al.  Towards Open Set Deep Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Silvio Savarese,et al.  Learning Transferrable Representations for Unsupervised Domain Adaptation , 2016, NIPS.

[14]  Kate Saenko,et al.  VisDA: The Visual Domain Adaptation Challenge , 2017, ArXiv.

[15]  Qilong Wang,et al.  Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Terrance E. Boult,et al.  Multi-class Open Set Recognition Using Probability of Inclusion , 2014, ECCV.

[18]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[19]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[21]  Mengjie Zhang,et al.  Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation , 2016, ECCV.

[22]  Trevor Darrell,et al.  FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation , 2016, ArXiv.

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

[24]  Kristen Grauman,et al.  Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation , 2013, ICML.

[25]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[26]  Juergen Gall,et al.  Open Set Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[28]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Dumitru Erhan,et al.  Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[31]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[33]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[35]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.