Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining previously learned knowledge. To deal with both drifts, we propose variational domain-agnostic feature replay, an approach that is composed of three components: an inference module that filters the input data into domain-agnostic representations, a generative module that facilitates knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We address the two fundamental scenarios in continuous domain adaptation, demonstrating the effectiveness of our proposed approach for practical usage.

[1]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

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

[3]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

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

[5]  Chong Wang,et al.  Stochastic variational inference , 2012, J. Mach. Learn. Res..

[6]  Trevor Darrell,et al.  Adapting to Continuously Shifting Domains , 2018, ICLR.

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

[8]  Barbara Caputo,et al.  AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Lantao Yu,et al.  Improving Unsupervised Domain Adaptation with Variational Information Bottleneck , 2020, ECAI.

[10]  Gregory Ditzler,et al.  Learning in Nonstationary Environments: A Survey , 2015, IEEE Computational Intelligence Magazine.

[11]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[12]  Yee Whye Teh,et al.  Progress & Compress: A scalable framework for continual learning , 2018, ICML.

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

[14]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[15]  Richard E. Turner,et al.  Variational Continual Learning , 2017, ICLR.

[16]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Luc Van Gool,et al.  DLOW: Domain Flow for Adaptation and Generalization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[19]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[20]  Marc'Aurelio Ranzato,et al.  Gradient Episodic Memory for Continual Learning , 2017, NIPS.

[21]  J. C. Schlimmer,et al.  Incremental learning from noisy data , 2004, Machine Learning.

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

[23]  Zijian Li,et al.  Learning Disentangled Semantic Representation for Domain Adaptation , 2019, IJCAI.

[24]  Junqing Yu,et al.  Significance-Aware Information Bottleneck for Domain Adaptive Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Davide Maltoni,et al.  Latent Replay for Real-Time Continual Learning , 2019, ArXiv.

[26]  David Rolnick,et al.  Experience Replay for Continual Learning , 2018, NeurIPS.

[27]  L. Gool,et al.  DLOW: Domain Flow for Adaptation and Generalization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Yuchen Zhang,et al.  Bridging Theory and Algorithm for Domain Adaptation , 2019, ICML.

[29]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[30]  Philip S. Yu,et al.  A General Framework for Mining Concept-Drifting Data Streams with Skewed Distributions , 2007, SDM.

[31]  Alexander A. Alemi,et al.  Deep Variational Information Bottleneck , 2017, ICLR.

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

[33]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[34]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

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

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

[37]  Gerhard Widmer,et al.  Effective Learning in Dynamic Environments by Explicit Context Tracking , 1993, ECML.

[38]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[39]  Gerhard Widmer,et al.  Learning in the Presence of Concept Drift and Hidden Contexts , 1996, Machine Learning.

[40]  Kate Saenko,et al.  Domain Agnostic Learning with Disentangled Representations , 2019, ICML.

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

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

[43]  Bogdan Raducanu,et al.  Memory Replay GANs: Learning to Generate New Categories without Forgetting , 2018, NeurIPS.

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

[45]  Alex Bewley,et al.  Incremental Adversarial Domain Adaptation for Continually Changing Environments , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[46]  Alexey Tsymbal,et al.  The problem of concept drift: definitions and related work , 2004 .

[47]  Jakub M. Tomczak,et al.  DIVA: Domain Invariant Variational Autoencoders , 2019, DGS@ICLR.

[48]  Trevor Darrell,et al.  Continuous Manifold Based Adaptation for Evolving Visual Domains , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[50]  B. McNaughton,et al.  Replay of Neuronal Firing Sequences in Rat Hippocampus During Sleep Following Spatial Experience , 1996, Science.

[51]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..