Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

[1]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[2]  Larry S. Davis,et al.  Exploiting local features from deep networks for image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[3]  Cordelia Schmid,et al.  Aggregating local descriptors into a compact image representation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Ming Yang,et al.  Conditional Generative Adversarial Network for Structured Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

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

[11]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[12]  Abhinav Gupta,et al.  ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[14]  Gabriela Csurka,et al.  Domain Adaptation for Visual Applications: A Comprehensive Survey , 2017, ArXiv.

[15]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[18]  Tomás Pajdla,et al.  NetVLAD: CNN Architecture for Weakly Supervised Place Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

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

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

[23]  Ivor W. Tsang,et al.  Hybrid Heterogeneous Transfer Learning through Deep Learning , 2014, AAAI.

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

[25]  Rick Siow Mong Goh,et al.  Transfer Hashing: From Shallow to Deep , 2018, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[28]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Jianhua Dai,et al.  Unsupervised Representation Learning With Long-Term Dynamics for Skeleton Based Action Recognition , 2018, AAAI.

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

[31]  Florent Perronnin,et al.  Fisher Kernels on Visual Vocabularies for Image Categorization , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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