Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target domain. However, algorithm comparison is cumbersome in Deep UDA due to the absence of accurate and standardized model selection method, posing an obstacle to further advances in the field. Existing model selection methods for Deep UDA are either highly biased, restricted, unstable, or even controversial (requiring labeled target data). To this end, we propose Deep Embedded Validation (DEV), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance. The variance is further reduced by the technique of control variate. The efficacy of the method has been justified both theoretically and empirically.

[1]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[2]  Steffen Bickel,et al.  Discriminative learning for differing training and test distributions , 2007, ICML '07.

[3]  Tinne Tuytelaars,et al.  Unsupervised Visual Domain Adaptation Using Subspace Alignment , 2013, 2013 IEEE International Conference on Computer Vision.

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

[5]  Kamyar Azizzadenesheli,et al.  Regularized Learning for Domain Adaptation under Label Shifts , 2019, ICLR.

[6]  Alexander J. Smola,et al.  Detecting and Correcting for Label Shift with Black Box Predictors , 2018, ICML.

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

[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]  David J. Kriegman,et al.  Image to Image Translation for Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Yishay Mansour,et al.  Learning Bounds for Importance Weighting , 2010, NIPS.

[12]  Michael I. Jordan,et al.  Conditional Adversarial Domain Adaptation , 2017, NeurIPS.

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

[14]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

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

[16]  Pedro H. O. Pinheiro,et al.  Unsupervised Domain Adaptation with Similarity Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Kate Saenko,et al.  VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[19]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[20]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

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

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

[23]  Koby Crammer,et al.  Learning Bounds for Domain Adaptation , 2007, NIPS.

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

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

[26]  Bernhard Schölkopf,et al.  On causal and anticausal learning , 2012, ICML.

[27]  Xin Pan,et al.  YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[29]  Tatsuya Harada,et al.  Open Set Domain Adaptation by Backpropagation , 2018, ECCV.

[30]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[32]  A. Rényi On Measures of Entropy and Information , 1961 .

[33]  Qiang Yang,et al.  Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning , 2010, ECML/PKDD.

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

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