Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature representations for this purpose using a global distribution alignment objective which does not take into account the finer class specific structure in the source and target domains. We address this issue in our work and propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. ILA-DA simultaneously accounts for intra-class clustering as well as inter-class separation among the categories, resulting in less noisy classifier boundaries, improved transferability and increased accuracy. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets and provide insights into the proposed alignment approach. Code will be made publicly available at https://github.com/astuti/ILA-DA.

[1]  Kaiming He,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Vittorio Murino,et al.  Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation , 2017, ICLR.

[4]  Yi Yang,et al.  Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization , 2018, ECCV.

[5]  Zsolt Kira,et al.  Neural network-based clustering using pairwise constraints , 2015, ArXiv.

[6]  Daniel Cremers,et al.  Associative Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[8]  Yi Yang,et al.  Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Stella X. Yu,et al.  Unsupervised Feature Learning via Non-parametric Instance Discrimination , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[11]  Ali Razavi,et al.  Data-Efficient Image Recognition with Contrastive Predictive Coding , 2019, ICML.

[12]  Belur V. Dasarathy Nearest unlike neighbor (NUN): an aid to decision confidence estimation , 1995 .

[13]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[14]  Rogério Schmidt Feris,et al.  Co-regularized Alignment for Unsupervised Domain Adaptation , 2018, NeurIPS.

[15]  Issam H. Laradji,et al.  M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning , 2018, Domain Adaptation for Visual Understanding.

[16]  Silvio Savarese,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Mehrtash Tafazzoli Harandi,et al.  Distribution-Matching Embedding for Visual Domain Adaptation , 2016, J. Mach. Learn. Res..

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

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

[20]  Nicolas Courty,et al.  DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation , 2018, ECCV.

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

[22]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[24]  Padraig Cunningham,et al.  Generating Estimates of Classification Confidence for a Case-Based Spam Filter , 2005, ICCBR.

[25]  Mikhail Khodak,et al.  A Theoretical Analysis of Contrastive Unsupervised Representation Learning , 2019, ICML.

[26]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[27]  Ali Farhadi,et al.  Watching the World Go By: Representation Learning from Unlabeled Videos , 2020, ArXiv.

[28]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Pietro Perona,et al.  Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Zsolt Kira,et al.  Multi-class Classification without Multi-class Labels , 2019, ICLR.

[31]  Yair Movshovitz-Attias,et al.  No Fuss Distance Metric Learning Using Proxies , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[32]  Qi Qian,et al.  SoftTriple Loss: Deep Metric Learning Without Triplet Sampling , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[34]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[35]  Deepak S. Turaga,et al.  Cross domain distribution adaptation via kernel mapping , 2009, KDD.

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

[37]  Nicolas Courty,et al.  Optimal Transport for Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Suha Kwak,et al.  Proxy Anchor Loss for Deep Metric Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[40]  Yunbo Wang,et al.  Progressive Adversarial Networks for Fine-Grained Domain Adaptation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[43]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

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

[45]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

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

[47]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

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

[49]  Jianmin Wang,et al.  Multi-Adversarial Domain Adaptation , 2018, AAAI.

[50]  Lorenzo Bruzzone,et al.  Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Chuan Chen,et al.  Learning Semantic Representations for Unsupervised Domain Adaptation , 2018, ICML.

[52]  Chong-Wah Ngo,et al.  Transferrable Prototypical Networks for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[54]  Sinisa Todorovic,et al.  Ensemble Deep Manifold Similarity Learning Using Hard Proxies , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[56]  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.

[57]  Dong Xu,et al.  Collaborative and Adversarial Network for Unsupervised Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[58]  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).

[59]  Yun Fu,et al.  Robust Transfer Metric Learning for Image Classification , 2017, IEEE Transactions on Image Processing.

[60]  Chen-Yu Lee,et al.  Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[62]  Koray Kavukcuoglu,et al.  Learning word embeddings efficiently with noise-contrastive estimation , 2013, NIPS.

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

[64]  Ivan Laptev,et al.  Deep Metric Learning Beyond Binary Supervision , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[65]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[66]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

[67]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[68]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[69]  Yi Yang,et al.  Contrastive Adaptation Network for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[70]  Bo Geng,et al.  DAML: Domain Adaptation Metric Learning , 2011, IEEE Transactions on Image Processing.

[71]  Yu-Chiang Frank Wang,et al.  Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[72]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[73]  Dacheng Tao,et al.  Deep Metric Learning With Tuplet Margin Loss , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

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

[76]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[77]  Xiang Yu,et al.  Unsupervised Domain Adaptation for Distance Metric Learning , 2018, International Conference on Learning Representations.

[78]  Matthew R. Scott,et al.  Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[79]  Tieniu Tan,et al.  Exploring uncertainty in pseudo-label guided unsupervised domain adaptation , 2019, Pattern Recognit..

[80]  Liang Lin,et al.  Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[81]  Junzhou Huang,et al.  Progressive Feature Alignment for Unsupervised Domain Adaptation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).