Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks

(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains (Multi-target DA). In this paper, we consider a more realistic transfer scenario: our target domain is comprised of multiple sub-targets implicitly blended with each other so that learners could not identify which sub-target each unlabeled sample belongs to. This Blending-target Domain Adaptation (BTDA) scenario commonly appears in practice and threatens the validities of existing DA algorithms, due to the presence of domain gaps and categorical misalignments among these hidden sub-targets. To reap the transfer performance gains in this new scenario, we propose Adversarial Meta-Adaptation Network (AMEAN). AMEAN entails two adversarial transfer learning processes. The first is a conventional adversarial transfer to bridge our source and mixed target domains. To circumvent the intra-target category misalignment, the second process presents as ``learning to adapt'': It deploys an unsupervised meta-learner receiving target data and their ongoing feature-learning feedbacks, to discover target clusters as our ``meta-sub-target'' domains. This meta-sub-targets auto-design our meta-sub-target adaptation loss, which is capable to progressively eliminate the implicit category mismatching in our mixed target. We evaluate AMEAN and a variety of DA algorithms in three benchmarks under the BTDA setup. Empirical results show that BTDA is a quite challenging transfer setup for most existing DA algorithms, yet AMEAN significantly outperforms these state-of-the-art baselines and effectively restrains the negative transfer effects in BTDA.

[1]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[2]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[3]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, ICCV.

[4]  Karsten M. Borgwardt,et al.  Covariate Shift by Kernel Mean Matching , 2009, NIPS 2009.

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

[6]  Ali Farhadi,et al.  Unsupervised Deep Embedding for Clustering Analysis , 2015, ICML.

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

[8]  Martial Hebert,et al.  Low-Shot Learning from Imaginary Data , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Rong Yan,et al.  Cross-domain video concept detection using adaptive svms , 2007, ACM Multimedia.

[10]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  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.

[12]  Sergey Levine,et al.  Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

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

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

[15]  Liang Lin,et al.  Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Jianping Yin,et al.  Improved Deep Embedded Clustering with Local Structure Preservation , 2017, IJCAI.

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

[18]  Cewu Lu,et al.  Virtual to Real Reinforcement Learning for Autonomous Driving , 2017, BMVC.

[19]  Eric P. Xing,et al.  AutoLoss: Learning Discrete Schedules for Alternate Optimization , 2018, ICLR 2018.

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

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

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

[23]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[24]  Eric P. Xing,et al.  Real-to-Virtual Domain Unification for End-to-End Autonomous Driving , 2018, ECCV.

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

[26]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

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

[28]  Yishay Mansour,et al.  Domain Adaptation with Multiple Sources , 2008, NIPS.

[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]  Sonia Chernova,et al.  Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer , 2018, ArXiv.

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

[33]  Edwin Lughofer,et al.  Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning , 2017, ICLR.

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

[35]  Razvan Pascanu,et al.  Sim-to-Real Robot Learning from Pixels with Progressive Nets , 2016, CoRL.

[36]  Timnit Gebru,et al.  Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

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

[39]  Barbara Caputo,et al.  Boosting Domain Adaptation by Discovering Latent Domains , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Stefano Ermon,et al.  A DIRT-T Approach to Unsupervised Domain Adaptation , 2018, ICLR.

[41]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

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

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

[44]  Luc Van Gool,et al.  Domain Adaptive Faster R-CNN for Object Detection in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[46]  Huanhuan Yu,et al.  Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories , 2018, ArXiv.

[47]  Vladimir Pavlovic,et al.  Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach , 2018, IEEE Transactions on Image Processing.

[48]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[49]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[50]  Michael Naehrig,et al.  CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.

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