Attention Network Robustification for Person ReID

The task of person re-identification (ReID) has attracted growing attention in recent years with improving performance but lack of focus on real-world applications. Most state of the art methods use large pre-trained models, e.g., ResNet50 (~25M parameters), as their backbone, which makes it tedious to explore different architecture modifications. In this study, we focus on small-sized randomly initialized models which enable us to easily introduce network and training modifications suitable for person ReID public datasets and real-world setups. We show the robustness of our network and training improvements by outperforming state of the art results in terms of rank-1 accuracy and mAP on Market1501 (96.2, 89.7) and DukeMTMC (89.8, 80.3) with only 6.4M parameters and without using re-ranking. Finally, we show the applicability of the proposed ReID network for multi-object tracking.

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

[2]  Xiao-Ping Zhang,et al.  Deep learning-based methods for person re-identification: A comprehensive review , 2019, Neurocomputing.

[3]  Andrea Cavallaro,et al.  Omni-Scale Feature Learning for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Andrew Gordon Wilson,et al.  Averaging Weights Leads to Wider Optima and Better Generalization , 2018, UAI.

[5]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[6]  Rongrong Ji,et al.  Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Zhedong Zheng,et al.  Joint Discriminative and Generative Learning for Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  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).

[9]  Yang Yang,et al.  ABD-Net: Attentive but Diverse Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[10]  Wenjun Zeng,et al.  Densely Semantically Aligned Person Re-Identification , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Shaogang Gong,et al.  Harmonious Attention Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Xin Jin,et al.  Relation-Aware Global Attention , 2019, ArXiv.

[13]  Wei Jiang,et al.  SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification , 2018, J. Vis. Commun. Image Represent..

[14]  Cheng Wang,et al.  Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification , 2018, ECCV.

[15]  Zhi Zhang,et al.  Bag of Tricks for Image Classification with Convolutional Neural Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Andrew Gordon Wilson,et al.  A Simple Baseline for Bayesian Uncertainty in Deep Learning , 2019, NeurIPS.

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

[18]  Yinghuan Shi,et al.  MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification , 2018, ArXiv.

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

[20]  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.

[21]  Feiyue Huang,et al.  A Coarse-to-fine Pyramidal Model for Person Re-identification via Multi-Loss Dynamic Training , 2018, ArXiv.

[22]  Giorgos Tolias,et al.  Fine-Tuning CNN Image Retrieval with No Human Annotation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[24]  Yi Yang,et al.  A Discriminatively Learned CNN Embedding for Person Reidentification , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[25]  Nicu Sebe,et al.  Group Consistent Similarity Learning via Deep CRF for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

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

[29]  Yu Wu,et al.  Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[30]  Gang Wang,et al.  Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[31]  Houqiang Li,et al.  Local Convolutional Neural Networks for Person Re-Identification , 2018, ACM Multimedia.

[32]  Xuan Zhang,et al.  SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification , 2018, ACCV.

[33]  Jian Sun,et al.  AlignedReID: Surpassing Human-Level Performance in Person Re-Identification , 2017, ArXiv.

[34]  Xiong Chen,et al.  Learning Discriminative Features with Multiple Granularities for Person Re-Identification , 2018, ACM Multimedia.

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

[36]  Ping Tan,et al.  Batch Feature Erasing for Person Re-identification and Beyond , 2018, ArXiv.

[37]  Muhittin Gokmen,et al.  Human Semantic Parsing for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Carlo Tomasi,et al.  Features for Multi-target Multi-camera Tracking and Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Tao Hu,et al.  Dynamic Task Decomposition for Probabilistic Tracking in Complex Scenes , 2014, 2014 22nd International Conference on Pattern Recognition.

[40]  Yifan Sun,et al.  SVDNet for Pedestrian Retrieval , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[42]  Stefan Roth,et al.  MOT16: A Benchmark for Multi-Object Tracking , 2016, ArXiv.

[43]  Long Chen,et al.  Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification , 2018, 2018 IEEE International Conference on Multimedia and Expo (ICME).