Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification

Although existing person re-identification (Re-ID) methods have shown impressive accuracy, most of them usually suffer from poor generalization on unseen target domain. Thus, generalizable person Re-ID has recently drawn increasing attention, which trains a model on source domains that generalizes well on unseen target domain without model updating. In this work, we propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID. It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model’s generalization by a meta-learning pipeline. Specifically, AdsNorm utilizes batch normalization layers to collect individual source domains’ characteristics, and maps source domains into a shared latent space by using these characteristics, where the domain relevance is measured by a distance function of different domain-specific normalization statistics and features. At the testing stage, AdsNorm projects images from unseen target domain into the same latent space, and adaptively integrates the domain-specific features carrying the source distributions by domain relevance for learning more generalizable aggregated representation on unseen target domain. Considering that target domain is unavailable during training, a meta-learning algorithm combined with a customized relation loss is proposed to optimize an effective and efficient ensemble model. Extensive experiments demonstrate that AdsNorm outperforms the state-of-the-art methods. The code is available at: https://github.com/hzphzp/AdsNorm.

[1]  Barbara Caputo,et al.  Domain Generalization with Domain-Specific Aggregation Modules , 2018, GCPR.

[2]  Yi Yang,et al.  Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[4]  Zheng-Jun Zha,et al.  Adaptive Transfer Network for Cross-Domain Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jiwen Lu,et al.  Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification , 2020, ECCV.

[6]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Xiaogang Wang,et al.  Joint Detection and Identification Feature Learning for Person Search , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaogang Wang,et al.  Locally Aligned Feature Transforms across Views , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Shaogang Gong,et al.  Unsupervised Cross-Dataset Transfer Learning for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Alberto L. Sangiovanni-Vincentelli,et al.  Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Shaogang Gong,et al.  Associating Groups of People , 2009, BMVC.

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

[13]  Feng Zheng,et al.  Dual Distribution Alignment Network for Generalizable Person Re-Identification , 2020, AAAI.

[14]  Jiaying Liu,et al.  Revisiting Batch Normalization For Practical Domain Adaptation , 2016, ICLR.

[15]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

[16]  Kecheng Zheng,et al.  Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification , 2020, AAAI.

[17]  Cuiling Lan,et al.  Relation-Aware Global Attention for Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Nicu Sebe,et al.  Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[21]  Tieniu Tan,et al.  Learning Domain Invariant Representations for Generalizable Person Re-Identification , 2021, ArXiv.

[22]  Wei Li,et al.  Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  Shaogang Gong,et al.  Person Re-Identification by Deep Joint Learning of Multi-Loss Classification , 2017, IJCAI.

[25]  Qi Tian,et al.  Scalable Person Re-identification on Supervised Smoothed Manifold , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Tomokazu Murakami,et al.  Augmented Hard Example Mining for Generalizable Person Re-Identification , 2019, ArXiv.

[27]  Changick Kim,et al.  Meta Batch-Instance Normalization for Generalizable Person Re-Identification , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Xin Jin,et al.  Semantics-Aligned Representation Learning for Person Re-identification , 2019, AAAI.

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

[30]  Cuiling Lan,et al.  Style Normalization and Restitution for Generalizable Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[32]  Yunchao Wei,et al.  Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[33]  Tao Xiang,et al.  Generalizable Person Re-Identification by Domain-Invariant Mapping Network , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Sridha Sridharan,et al.  Correlation-aware Adversarial Domain Adaptation and Generalization , 2019, Pattern Recognit..

[35]  Longhui Wei,et al.  Person Transfer GAN to Bridge Domain Gap for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[36]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Alex C. Kot,et al.  Multi-Domain Adversarial Feature Generalization for Person Re-Identification , 2020, IEEE Transactions on Image Processing.

[38]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[39]  Slawomir Bak,et al.  Domain Adaptation through Synthesis for Unsupervised Person Re-identification , 2018, ECCV.

[40]  Xiaobin Liu,et al.  Domain Adaptive Person Re-Identification via Coupling Optimization , 2020, ACM Multimedia.

[41]  Yu-Chiang Frank Wang,et al.  Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[42]  Ling Shao,et al.  Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification , 2020, ACM Multimedia.

[43]  Shaogang Gong,et al.  Multi-camera activity correlation analysis , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[44]  Hai Tao,et al.  Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features , 2008, ECCV.

[45]  Qiuqi Ruan,et al.  Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice , 2019, BMVC.

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

[47]  Ling Shao,et al.  Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification , 2020, ECCV.

[48]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.