RANDnet: Vehicle Re-Identification with Relation Attention and Nuance–Disparity Masks
Source abstract
Abstract
Vehicle re-identification (vehicle ReID) is designed to recognize all instances of a specific vehicle across various camera viewpoints, facing significant challenges such as high similarity among different vehicles from the same viewpoint and substantial variance for the same vehicle across different viewpoints. In this paper, we introduce the RAND network, which is equipped with relation attention mechanisms, nuance, and disparity masks to tackle these issues effectively. The disparity mask specifically targets the automatic suppression of irrelevant foreground and background noise, while the nuance mask reveals less obvious, sub-discriminative regions to enhance the overall feature robustness. Additionally, our relation attention module, which incorporates an advanced transformer architecture, significantly reduces intra-class distances, thereby improving the accuracy of vehicle identification across diverse viewpoints. The performance of our approach has been thoroughly evaluated on widely recognized datasets such as VeRi-776 and VehicleID, where it demonstrates superior effectiveness and competes robustly with other leading methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China
Key Laboratory of Data Science and Intelligent Computing, Institute of International Innovation, Beihang University, Yuhang District, Hangzhou 311115, China
Sinenux, Jinan 250014, China
Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence of Ministry of Education, Macao Polytechnic University, Macau, China
Funding
National Key RD Program of China · National Natural Science Foundation of China · Open Fund of the State Key Laboratory of Software Development Environment · Haiyou Plan Fund
References (55)
Show source-provided references
1. Song, Z., Li, D., Chen, Z., and Yang, W. (2023). Unsupervised Vehicle Re-Identification Method Based on Source-Free Knowledge Transfer. Appl. Sci., 13.10.20944/preprints202309.0754.v1 ↗
2. Mendes, D., Correia, S., Jorge, P., Brandão, T., Arriaga, P., and Nunes, L. (2023). Multi-Camera Person Re-Identification Based on Trajectory Data. Appl. Sci., 13.10.3390/app132011578 ↗
3. Yin, W., Peng, Y., Ye, Z., and Liu, W. (2023). A Novel Dual Mixing Attention Network for UAV-Based Vehicle Re-Identification. Appl. Sci., 13.10.20944/preprints202309.1081.v1 ↗
4. Wang, X., Hu, X., Liu, P., and Tang, R. (2023). A Person Re-Identification Method Based on Multi-Branch Feature Fusion. Appl. Sci., 13.10.3390/app132111707 ↗
5. Liu, C., Xue, J., Wang, Z., and Zhu, A. (2023). PMG—Pyramidal Multi-Granular Matching for Text-Based Person Re-Identification. Appl. Sci., 13.10.3390/app132111876 ↗
6. Liu, X., Liu, W., Ma, H., and Fu, H. (2016, January 11–15). Large-scale vehicle re-identification in urban surveillance videos. Proceedings of the 2016 IEEE International Conference on Multimedia and Expo (ICME), Seattle, WA, USA.10.1109/ICME.2016.7553002 ↗
7. Exploring spatial significance via hybrid pyramidal graph network for vehicle re-identification10.1109/TITS.2021.3086142 ↗
8. Vehiclenet: Learning robust visual representation for vehicle re-identification10.1109/TMM.2020.3014488 ↗
9. Chen, B., Deng, W., and Hu, J. (November, January 27). Mixed high-order attention network for person re-identification. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00046 ↗
10. Zhang, Z., Lan, C., Zeng, W., Jin, X., and Chen, Z. (2020, January 13–19). Relation-aware global attention for person re-identification. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00325 ↗
11. Wang, Z., Tang, L., Liu, X., Yao, Z., Yi, S., Shao, J., Yan, J., Wang, S., Li, H., and Wang, X. (2017, January 22–29). Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.49 ↗
12. Disentangled Feature Learning Network and a Comprehensive Benchmark for Vehicle ReIdentification10.1109/TPAMI.2021.3099253 ↗
13. AttributeNet: Attribute enhanced vehicle re-identification
14. Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
15. Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., and Wei, Y. (November, January 27). Vehicle re-identification with viewpoint-aware metric learning. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00837 ↗
16. Zhou, Y., and Shao, L. (2018, January 18–23). Aware attentive multi-view inference for vehicle re-identification. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00679 ↗
17. Vehicle re-identification by adversarial bi-directional lstm network
18. Zhu, X., Luo, Z., Fu, P., and Ji, X. (2020, January 14–19). VOC-RelD: Vehicle Re-identification based on Vehicle-Orientation-Camera. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00309 ↗
19. He, B., Li, J., Zhao, Y., and Tian, Y. (2019, January 15–20). Part-regularized near-duplicate vehicle re-identification. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00412 ↗
20. Liu, X., Zhang, S., Huang, Q., and Gao, W. (2018). Ram: A region-aware deep model for vehicle re-identification. arXiv, 1–6.10.1109/ICME.2018.8486589 ↗
21. ES-Net: Erasing Salient Parts to Learn More in Re-Identification10.1109/TIP.2020.3046904 ↗
22. Meng, D., Li, L., Liu, X., Li, Y., Yang, S., Zha, Z.-J., Gao, X., Wang, S., and Huang, Q. (2020, January 13–19). Parsing-based View-aware Embedding Network for Vehicle Re-Identification. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00713 ↗
23. Group-group loss-based global-regional feature learning for vehicle re-identification10.1109/TIP.2019.2950796 ↗
24. Shen, Y., Xiao, T., Li, H., Yi, S., and Wang, X. (2017, January 22–29). Learning deep neural networks for vehicle re-id with visual-spatio-temporal path proposals. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.210 ↗
25. The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification
26. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural Machine Translation by Jointly Learning to Align and Translate. arXiv.
27. Bollmann, M., Bingel, J., and Søgaard, A. (August, January 30). Learning attention for historical text normalization by learning to pronounce. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, BC, Canada.
28. Xu, M., Wong, D.F., Yang, B., Zhang, Y., and Chao, L.S. (August, January 28). Leveraging Local and Global Patterns for Self-Attention Networks. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
29. Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention
30. Luong, T., Pham, H., and Manning, C.D. (2015). Effective Approaches to Attention-based Neural Machine Translation. arXiv.10.18653/v1/D15-1166 ↗
31. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is All you Need. arXiv, pp. 5998–6008.
32. Shaw, P., Uszkoreit, J., and Vaswani, A. (2018). Self-Attention with Relative Position Representations. arXiv, pp. 464–468.10.18653/v1/N18-2074 ↗
33. SAL: Selection and Attention Losses for Weakly Supervised Semantic Segmentation10.1109/TMM.2020.2991592 ↗
34. Co-Saliency Detection With Co-Attention Fully Convolutional Network10.1109/TCSVT.2020.2992054 ↗
35. Hu, J., Shen, L., and Sun, G. (2018). Squeeze-and-excitation networks. arXiv, pp. 7132–7141.10.1109/CVPR.2018.00745 ↗
36. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017). Residual attention network for image classification. arXiv, pp. 3156–3164.10.1109/CVPR.2017.683 ↗
37. Woo, S., Park, J., Lee, J.-Y., and In, S.K. (2018). Cbam: Convolutional block attention module. arXiv, pp. 3–19.10.1007/978-3-030-01234-2_1 ↗
38. Park, J., Woo, S., Lee, J., and Kweon, I.S. (2018). BAM: Bottleneck Attention Module. arXiv, pp. 147–160.
39. Bello, I., Zoph, B., Vaswani, A., Shlens, J., and Le, Q.V. (2019). Attention augmented convolutional networks. arXiv, pp. 3286–3295.10.1109/ICCV.2019.00338 ↗
40. Li, W., Zhu, X., and Gong, S. (2018). Harmonious attention network for person re-identification. arXiv, pp. 2285–2294.10.1109/CVPR.2018.00243 ↗
41. Liu, S., Johns, E., and Davison, A.J. (2019). End-to-end multi-task learning with attention. arXiv, pp. 1871–1880.10.1109/CVPR.2019.00197 ↗
42. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
43. Liu, X., Liu, W., Mei, T., and Ma, H. (2016, January 11–14). A deep learning-based approach to progressive vehicle re-identification for urban surveillance. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46475-6_53 ↗
44. Liu, H., Tian, Y., Yang, Y., Pang, L., and Huang, T. (2016, January 27–30). Deep relative distance learning: Tell the difference between similar vehicles. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.238 ↗
45. Random Erasing Data Augmentation10.1609/aaai.v34i07.7000 ↗
46. Khorramshahi, P., Kumar, A., Peri, N., Rambhatla, S.S., Chen, J.-C., and Chellappa, R. (November, January 27). A dual-path model with adaptive attention for vehicle re-identification. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic iof Korea.10.1109/ICCV.2019.00623 ↗
47. Zhang, X., Zhang, R., Cao, J., Gong, D., You, M., and Shen, C. (2019). Part-Guided Attention Learning for Vehicle Re-Identification. arXiv.
48. Lou, Y., Bai, Y., Liu, J., Wang, S., and Duan, L. (2019, January 15–20). Veri-wild: A large dataset and a new method for vehicle re-identification in the wild. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00335 ↗
49. Embedding adversarial learning for vehicle re-identification10.1109/TIP.2019.2902112 ↗
50. He, S., Luo, H., Wang, P., Wang, F., Li, H., and Jiang, W. (2021, January 10–17). Transreid: Transformer-based object re-identification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.01474 ↗
51. Self-supervised geometric features discovery via interpretable attention for vehicle re-identification and beyond
52. Partition and reunion: A viewpoint-aware loss for vehicle re-identification
53. Weakly-supervised part-attention and mentored networks for vehicle re-identification10.1109/TCSVT.2022.3197844 ↗
54. He, L., Liao, X., Liu, W., Liu, X., Cheng, P., and Mei, T. (2020). Fastreid: A pytorch toolbox for general instance re-identification. arXiv.
55. Zhao, J., Zhao, Y., Li, J., Yan, K., and Tian, Y. (2021, January 10–17). Heterogeneous relational complement for vehicle re-identification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00027 ↗