Camera-Agnostic Person Re-Identification via Adversarial Disentangling Learning

Despite the success of single-domain person re-identification (ReID), current supervised models degrade dramatically when deployed to unseen domains, mainly due to the discrepancy across cameras. To tackle this issue, we propose an Adversarial Disentangling Learning (ADL) framework to decouple camera-related and ID-related features, which can be readily used for camera-agnostic person ReID. ADL adopts a discriminative way instead of the mainstream generative styles in disentangling methods, eg., GAN or VAE based, because for person ReID task only the information to discriminate IDs is needed, and more information to generate images are redundant and may be noisy. Specifically, our model involves a feature separation module that encodes images into two separate feature spaces and a disentangled feature learning module that performs adversarial training to minimize mutual information. We design an effective solution to approximate and minimize mutual information by transforming it into a discrimination problem. The two modules are co-designed to obtain strong generalization ability by only using source dataset. Extensive experiments on three public benchmarks show that our method outperforms the state-of-the-art generalizable person ReID model by a large margin. Our code is publicly available at https://github.com/luckyaci/ADL_ReID.

[1]  Jian-Huang Lai,et al.  Supplementary Material for “Unsupervised Person Re-identification by Soft Multilabel Learning” , 2019 .

[2]  Wei-Shi Zheng,et al.  Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  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).

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

[5]  Yang Hu,et al.  Cross Dataset Person Re-identification , 2014, ACCV Workshops.

[6]  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.

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

[8]  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).

[9]  Ling Shao,et al.  Interpretable and Generalizable Person Re-identification with Query-Adaptive Convolution and Temporal Lifting , 2019, ECCV.

[10]  Zhiming Luo,et al.  Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yang Yang,et al.  Adversarial Cross-Modal Retrieval , 2017, ACM Multimedia.

[12]  Zhedong Zheng,et al.  CamStyle: A Novel Data Augmentation Method for Person Re-Identification , 2019, IEEE Transactions on Image Processing.

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

[14]  Yi Yang,et al.  Camera Style Adaptation for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Liang Zheng,et al.  Re-ranking Person Re-identification with k-Reciprocal Encoding , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Huimin Lu,et al.  Ternary Adversarial Networks With Self-Supervision for Zero-Shot Cross-Modal Retrieval , 2020, IEEE Transactions on Cybernetics.

[17]  Yi Yang,et al.  Generalizing a Person Retrieval Model Hetero- and Homogeneously , 2018, ECCV.

[18]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[19]  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.

[20]  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).

[21]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[22]  Weihong Deng,et al.  Mixed High-Order Attention Network for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[23]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Chenggang Yan,et al.  Unsupervised Person Re-Identification via Softened Similarity Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  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.

[26]  Liang Zheng,et al.  Unsupervised Person Re-identification: Clustering and Fine-tuning , 2017 .

[27]  Shiliang Zhang,et al.  Unsupervised Person Re-Identification via Multi-Label Classification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Yang Zou,et al.  Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification , 2020, ECCV.

[29]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

[30]  Chuang Gan,et al.  Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering , 2019, AAAI.

[31]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[32]  Shengcai Liao,et al.  Clustering and Dynamic Sampling Based Unsupervised Domain Adaptation for Person Re-Identification , 2019, 2019 IEEE International Conference on Multimedia and Expo (ICME).

[33]  Francesco Solera,et al.  Performance Measures and a Data Set for Multi-target, Multi-camera Tracking , 2016, ECCV Workshops.

[34]  Amit K. Roy-Chowdhury,et al.  Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Tao Xiang,et al.  Pose-Normalized Image Generation for Person Re-identification , 2017, ECCV.

[36]  Jingkuan Song,et al.  Learnable Aggregating Net with Diversity Learning for Video Question Answering , 2019, ACM Multimedia.

[37]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[38]  Wei Jiang,et al.  Bag of Tricks and a Strong Baseline for Deep Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).