Abstract
Vehicle re-identification aims to retrieve the target vehicle from the image gallery quickly and accurately. Vehicle re-identification with deep learning has achieved considerable performance. However, most popular methods need construct complex network, which increases the calculation of network and difficulty of training. To balance performance and complexity, an efficient but lightweight network is proposed in this work. The designed network utilizes the global branch and the mask branch to extract the feature. The former can extract global feature efficiently. The latter can remove the changeable background based on the proposed mask-mapping module, which can map mask to feature map and adjust feature map dynamically. And then, the features from the original image and the mask-mapping module are fused to generate the final feature for vehicle re-identification. Besides, a novel center-constraint triplet loss is designed to optimize the proposed network and excavate more discriminate feature. Different from triplet loss, the proposed loss can consider more extra samples and constrain the center from positive sample set as well as negative sample set. To enhance the difference between hard samples and simple samples, an unequal weight strategy is embedded in this loss. The proposed method achieves 78.7% mAP with 95.4% Rank-1 on VeRi-776, and 84.3%, 80.7%, and 80.1% Rank-1 on three subsets from VehicleID, which demonstrates the effectiveness of the proposed method.
Similar content being viewed by others
References
Liu X, Liu W, Ma H, Fu H (2016) Large-scale vehicle re-identification in urban surveillance videos. In: IEEE International conference on multimedia and expo, pp. 1–6
Liu X, Wu L, Tao M, Ma H (2016) A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In: European conference on computer vision, pp. 869–884
Chao S, Nong S, Gao C, Lei Z(2017) Vehicle re-identification by fusing multiple deep neural networks. In: International conference on image processing theory, tools and applications, pp. 1–6
Zhong K, Wang Y, Pei J, Tang S, Han Z (2021) Super efficiency SBM-DEA and neural network for performance evaluation. Inf Process Manag 58(6):102728
Wang Z, Tang L, Liu X, Yao Z, Wang X (2017) Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification. In: IEEE International conference on computer vision, pp. 379–387
Ma X, Zhu K, Guo H, Wang J, Miao Q (2019) Vehicle re-identification with refined part model. In: IEEE International conference on multimedia and expo workshops, pp. 603–606
Schroff F, Kalenichenko D, Facenet Philbin. J (2015) A unified embedding for face recognition and clustering. In: IEEE Conference on computer vision and pattern recognition, pp. 815–823
Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification
Li Y, Li Y, Yan H, Liu J (2017) Deep joint discriminative learning for vehicle re-identification and retrieval. In: IEEE International conference on image processing, pp. 395–399
Tang Y, Wu D, Jin Z, Zou W, Li X (2017) Multi-modal metric learning for vehicle re-identification in traffic surveillance environment. In: IEEE International conference on image processing, pp. 2254–2258
Tang Z, Naphada M, Birchfiels S, Tremblay J, Hodge W, Kumar R, Wang S, Yang X (2019) Pamtri: Pose-aware multi-task learning for vehicle re-identification using highly randomized synthetic data. In: IEEE CVF International conference on computer vision, pp. 211–220
Gupta A, Chittrarasu A, Balakrishnan R (2020) Vehicle re-identification using relative entropy representation and gated recurrent unit networks. Procedia Comput Sci 171:508–513
Teng S, Zhang S, Huang Q, Sebe N (2021) Viewpoint and scale consistency reinforcement for UAV vehicle re-identification. Int J Comput Vision 129:719–735
Wang H, Wang Y, Zhou Z, Ji X, Gong D, Zhou J, Li Z, Liu W (2018) Cosface: Large margin cosine loss for deep face recognition. In IEEE CVF Conference on Computer Vision and Pattern Recognition, pp. 5265–5274
Sun Y, Cheng C, Zhang Y, Zhang C, Zheng L, Wang Z, Wei Y (2020) Circle loss: a unified perspective of pair similarity optimization. In: IEEE CVF conference on computer vision and pattern recognition, pp. 6397–6406
Zhang Y, Liu D, Zha Z (2017) Improving triplet-wise training of convolutional neural network for vehicle re-identification. In: IEEE International conference on multimedia and expo, pp. 1386–1391
Guo H, Zhao C, Liu Z, Wang J, Lu H (2018) Learning coarse-to-fine structured feature embedding for vehicle re-identification. In: AAAI Conference on Artificial Intelligence, pp. 6853–6860
Gu J, Jiang W, Luo H, Yu H (2021) An efficient global representation constrained by angular triplet loss for vehicle re-identification. Pattern Anal Appl 24(1):367–379
Chen X, Sui H, Fang J, Zhou M, Wu C (2020) Multi-proxy constraint loss for vehicle re-identification. Sensors 20(18):1–15
Zhong Z, Zheng L, Kang G, Li S, Yang L (2017) Random erasing data augmentation. Proc. AAAI Conf. Artif. Intell. 34:13001–13008
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on computer vision and pattern recognition, pp. 770–778
He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. In IEEE International conference on computer vision, pp. 2980–2988
Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. In: International conference on machine learning, pp. 507–516
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L(2017) Sphereface: Deep hypersphere embedding for face recognition. In: IEEE Conference on computer vision and pattern recognition, pp. 6738–6746
Wang F, Cheng J, Liu W, Liu H (2018) Additive margin softmax for face verification. IEEE Signal Processing Letters 25(7):926–930
Chen W, Chen X, Zhang J, Huang K (2017) Beyond triplet loss: A deep quadruplet network for person re-identification. In: IEEE Conference on computer vision and pattern recognition, pp. 1320–1329
Liu X, Liu W, Mei T, Ma H (2018) Provid: Progressive and multimodal vehicle reidentification for large-scale urban surveillance. IEEE Trans Multimed 20(3):645–658
Liu H, Tian Y, Wang Y, Pang L, Huang T (2016) Deep relative distance learning: tell the difference between similar vehicles. In: IEEE Conference on computer vision and pattern recognition, pp. 2167–2175
Pei J, Zhong K, Li J, Xu J, Wang X (2021) ECNN: evaluating a cluster-neural network model for city innovation capability. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06471-z
Teng S, Liu X, Zhang S, Huang Q (2018) Scan: spatial and channel attention network for vehicle re-identification. In Pacific rim conference on multimedia, pp. 350–361
Shen Y, Xiao T, Li H, Yi S, Wang X (2017) Learning deep neural networks for vehicle re-id with visual-spatio-temporal path proposals. In: IEEE International conference on computer vision, pp. 1918–1927
Lou Y, Bai Y, Liu J, Wang S, Duan. Veri-wild L (2019) A large dataset and a new method for vehicle re-identification in the wild. In: IEEE CVF Conference on Computer Vision and Pattern Recognition, pp. 3230–3238
Chun R, Sun Y, Li Y, Liu Z, Zhang C, Wei Y (2019) Vehicle re-identification with viewpoint-aware metric learning. In: IEEE CVF International conference on computer vision, pp. 8281–8290
He B, Li J, Zhao Y, Tian Y (2019) Part-regularized near-duplicate vehicle re-identification. In: IEEE CVF Conference on computer vision and pattern recognition, pp. 3992–4000
Zhu R, Fang J, Xu H, Yu H, Xue J (2020) DCDLearn: multi-order deep cross-distance learning for vehicle re-identification
Hou J, Zeng H, Cai L, Zhu J, Chen J, Ma K (2019) Multi-label learning with multi-label smoothing regularization for vehicle re-identification. Neurocomputing 345:15–22
Zheng A, Lin X, Li C, He R, Tang J (2019) Attributes guided feature learning for vehicle re-identification
He X, Zhou Y, Zhou Z, Bai S, Bai X (2018) Triplet-center loss for multi-view 3D object retrieval. In: IEEE CVF conference on computer vision and pattern recognition, pp. 1945–1954
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest exists.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yu, Z., Zhu, M. Efficient but lightweight network for vehicle re-identification with center-constraint loss. Neural Comput & Applic 34, 12373–12384 (2022). https://doi.org/10.1007/s00521-021-06658-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06658-4