Learning to Diversify for Single Domain Generalization

Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability of multiple source domains, this paper considers a more realistic yet challenging scenario, namely Single Domain Generalization (Single-DG), where only one source domain is available for training. In this scenario, the limited diversity may jeopardize the model generalization on unseen target domains. To tackle this problem, we propose a style-complement module to enhance the generalization power of the model by synthesizing images from diverse distributions that are complementary to the source ones. More specifically, we adopt a tractable upper bound of mutual information (MI) between the generated and source samples and perform a two-step optimization iteratively: (1) by minimizing the MI upper bound approximation for each sample pair, the generated images are forced to be diversified from the source samples; (2) subsequently, we maximize the MI between the samples from the same semantic category, which assists the network to learn discriminative features from diverse-styled images. Extensive experiments on three benchmark datasets demonstrate the superiority of our approach, which surpasses the state-of-the-art single-DG methods by up to 25.14%. The code will be publicly available at https://github.com/BUserName/Learning_to_diversify

[1]  Marc Niethammer,et al.  Robust and Generalizable Visual Representation Learning via Random Convolutions , 2020, ICLR.

[2]  Dimitris N. Metaxas,et al.  Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness , 2020, NeurIPS.

[3]  Zijian Wang,et al.  Prototype-Matching Graph Network for Heterogeneous Domain Adaptation , 2020, ACM Multimedia.

[4]  Judy Hoffman,et al.  Learning to Balance Specificity and Invariance for In and Out of Domain Generalization , 2020, ECCV.

[5]  Ling Shao,et al.  Learning to Learn with Variational Information Bottleneck for Domain Generalization , 2020, ECCV.

[6]  Timothy M. Hospedales,et al.  Learning to Generate Novel Domains for Domain Generalization , 2020, ECCV.

[7]  Eric P. Xing,et al.  Self-Challenging Improves Cross-Domain Generalization , 2020, ECCV.

[8]  Zhe Gan,et al.  CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information , 2020, ICML.

[9]  Zi Huang,et al.  Progressive Graph Learning for Open-Set Domain Adaptation , 2020, ICML.

[10]  Ce Liu,et al.  Supervised Contrastive Learning , 2020, NeurIPS.

[11]  Xi Peng,et al.  Learning to Learn Single Domain Generalization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Tatsuya Harada,et al.  Domain Generalization Using a Mixture of Multiple Latent Domains , 2019, AAAI.

[13]  Daniel C. Castro,et al.  Domain Generalization via Model-Agnostic Learning of Semantic Features , 2019, NeurIPS.

[14]  Gurumurthy Swaminathan,et al.  d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Eric P. Xing,et al.  Learning Robust Global Representations by Penalizing Local Predictive Power , 2019, NeurIPS.

[16]  Trevor Darrell,et al.  Semi-Supervised Domain Adaptation via Minimax Entropy , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[17]  Fabio Maria Carlucci,et al.  Domain Generalization by Solving Jigsaw Puzzles , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Yongxin Yang,et al.  Episodic Training for Domain Generalization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Eric P. Xing,et al.  Learning Robust Representations by Projecting Superficial Statistics Out , 2018, ICLR.

[20]  Thomas G. Dietterich,et al.  Benchmarking Neural Network Robustness to Common Corruptions and Perturbations , 2018, ICLR.

[21]  Swami Sankaranarayanan,et al.  MetaReg: Towards Domain Generalization using Meta-Regularization , 2018, NeurIPS.

[22]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[23]  Barbara Caputo,et al.  Best Sources Forward: Domain Generalization through Source-Specific Nets , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[24]  Silvio Savarese,et al.  Generalizing to Unseen Domains via Adversarial Data Augmentation , 2018, NeurIPS.

[25]  Siddhartha Chaudhuri,et al.  Generalizing Across Domains via Cross-Gradient Training , 2018, ICLR.

[26]  Mei Wang,et al.  Deep Visual Domain Adaptation: A Survey , 2018, Neurocomputing.

[27]  Yongxin Yang,et al.  Learning to Generalize: Meta-Learning for Domain Generalization , 2017, AAAI.

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

[29]  Quinn Jones,et al.  Few-Shot Adversarial Domain Adaptation , 2017, NIPS.

[30]  Yongxin Yang,et al.  Deeper, Broader and Artier Domain Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Donald A. Adjeroh,et al.  Unified Deep Supervised Domain Adaptation and Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[33]  Gabriela Csurka,et al.  A Comprehensive Survey on Domain Adaptation for Visual Applications , 2017, Domain Adaptation in Computer Vision Applications.

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

[35]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

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

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

[38]  Mengjie Zhang,et al.  Domain Generalization for Object Recognition with Multi-task Autoencoders , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

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

[41]  Brian C. Lovell,et al.  Unsupervised Domain Adaptation by Domain Invariant Projection , 2013, 2013 IEEE International Conference on Computer Vision.

[42]  Bernhard Schölkopf,et al.  Domain Generalization via Invariant Feature Representation , 2013, ICML.

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

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

[45]  Avishek Saha,et al.  Co-regularization Based Semi-supervised Domain Adaptation , 2010, NIPS.

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

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

[48]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

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

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

[51]  Isabelle Guyon,et al.  Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.