Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention

Vehicle re-identification (re-id) is a fundamental problem for modern surveillance camera networks. Existing approaches for vehicle re-id utilize global features and local features for re-id by combining multiple subnetworks and losses. In this paper, we propose GLAMOR, or Global and Local Attention MOdules for Re-id. GLAMOR performs global and local feature extraction simultaneously in a unified model to achieve state-of-the-art performance in vehicle re-id across a variety of adversarial conditions and datasets (mAPs 80.34, 76.48, 77.15 on VeRi-776, VRIC, and VeRi-Wild, respectively). GLAMOR introduces several contributions: a better backbone construction method that outperforms recent approaches, group and layer normalization to address conflicting loss targets for re-id, a novel global attention module for global feature extraction, and a novel local attention module for self-guided part-based local feature extraction that does not require supervision. Additionally, GLAMOR is a compact and fast model that is 10x smaller while delivering 25% better performance.

[1]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[2]  Umakishore Ramachandran,et al.  STTR: A System for Tracking All Vehicles All the Time At the Edge of the Network , 2018, DEBS.

[3]  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).

[4]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[5]  Paramvir Bahl,et al.  Live Video Analytics at Scale with Approximation and Delay-Tolerance , 2017, NSDI.

[6]  Jun Wang,et al.  Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative , 2017, ArXiv.

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

[8]  Bernt Schiele,et al.  Multi-person Tracking by Multicut and Deep Matching , 2016, ECCV Workshops.

[9]  Geoffrey E. Hinton,et al.  Layer Normalization , 2016, ArXiv.

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

[11]  David Kappel,et al.  Deep Rewiring: Training very sparse deep networks , 2017, ICLR.

[12]  Xinyu Zhang,et al.  Real-time vehicle detection and tracking using improved histogram of gradient features and Kalman filters , 2018 .

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

[14]  Jenq-Neng Hwang,et al.  Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[15]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Shengcai Liao,et al.  Vehicle Re-Identification Using Quadruple Directional Deep Learning Features , 2018, IEEE Transactions on Intelligent Transportation Systems.

[17]  Erich Elsen,et al.  The State of Sparsity in Deep Neural Networks , 2019, ArXiv.

[18]  Bing He,et al.  Part-Regularized Near-Duplicate Vehicle Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[20]  Wenyu Liu,et al.  Multi-oriented Text Detection with Fully Convolutional Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[22]  Ling Shao,et al.  Vehicle Re-Identification by Adversarial Bi-Directional LSTM Network , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[23]  Jenq-Neng Hwang,et al.  Multi-Camera Tracking of Vehicles based on Deep Features Re-ID and Trajectory-Based Camera Link Models , 2019, CVPR Workshops.

[24]  Guillaume Charpiat,et al.  Multiple Object Tracking by Efficient Graph Partitioning , 2014, ACCV.

[25]  Xuan Zhang,et al.  Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project , 2017, CVPR 2017.

[26]  Shiliang Zhang,et al.  RAM: A Region-Aware Deep Model for Vehicle Re-Identification , 2018, 2018 IEEE International Conference on Multimedia and Expo (ICME).

[27]  Xianping Fu,et al.  Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification , 2020, Neurocomputing.

[28]  Ling Shao,et al.  Cross-View GAN Based Vehicle Generation for Re-identification , 2017, BMVC.

[29]  Rufeng Zhang,et al.  Part-Guided Attention Learning for Vehicle Re-Identification , 2019, ArXiv.

[30]  Erich Elsen,et al.  Exploring Sparsity in Recurrent Neural Networks , 2017, ICLR.

[31]  Xinyu Zhang,et al.  Part-Guided Attention Learning for Vehicle Instance Retrieval , 2019, IEEE Transactions on Intelligent Transportation Systems.

[32]  Tao Mei,et al.  A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance , 2016, ECCV.

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

[34]  Jenq-Neng Hwang,et al.  Multiple-kernel adaptive segmentation and tracking (MAST) for robust object tracking , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[36]  Bernt Schiele,et al.  Multiple People Tracking by Lifted Multicut and Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Thomas Brox,et al.  A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects , 2016, ArXiv.

[38]  Yi Yang,et al.  Unsupervised Person Re-identification , 2018, ACM Trans. Multim. Comput. Commun. Appl..

[39]  Shaogang Gong,et al.  Multi-Task Mutual Learning for Vehicle Re-Identification , 2019, CVPR Workshops.

[40]  Snehasis Mukherjee,et al.  Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification , 2019, Neurocomputing.

[41]  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.

[42]  Xiaogang Wang,et al.  Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[43]  Ran He,et al.  Attributes Guided Feature Learning for Vehicle Re-Identification , 2019, IEEE Transactions on Emerging Topics in Computational Intelligence.

[44]  Ling-Yu Duan,et al.  Group-Sensitive Triplet Embedding for Vehicle Reidentification , 2018, IEEE Transactions on Multimedia.

[45]  Ling-Yu Duan,et al.  Embedding Adversarial Learning for Vehicle Re-Identification , 2019, IEEE Transactions on Image Processing.

[46]  Kaiming He,et al.  Group Normalization , 2018, ECCV.

[47]  Ling-Yu Duan,et al.  VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Jenq-Neng Hwang,et al.  Tracking Human Under Occlusion Based on Adaptive Multiple Kernels With Projected Gradients , 2013, IEEE Transactions on Multimedia.

[49]  Xiaogang Wang,et al.  Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).