Unsupervise contrastive learning person re-identification Method based on Transfomer
DOI:
https://doi.org/10.54097/fcis.v3i1.6018Keywords:
Unsupervised learning, Person re-identification, Cluster-wise contrastive learning, Transformer-basedAbstract
Unsupervised learning person re-identification is a meaningful and challenging person retrieving problem resulting from its application on secure surveillance and missing of label. To handle the lack of person identities, CNN-based method has been proposed to use self-contrastive learning based on a memory dictionary. However, CNN's partial bias is not well addressed in the field of ReID. To overcome these limitations, we propose a transformer-based framework called (TransCC). Specifically, we take the ViT transformer encoder trained on ImageNet as the feature extraction network, which makes up for some disadvantage of the CNN model. In addition, to overcome the issue of cluster inconsistency in instance-based memory method, unique cluster vectors are used to represent clusters in Characteristic space stored in the memory dictionary. By updating the cluster centriods and calculating contrastive loss, the model can be optimized and learn person-identifying traits. The experiment results outperform that of most methods, which demonstrate the effectiveness of our approach on USL ReID.
Downloads
References
M. Zabłocki, K. Gosciewska, D. Frejlichowski, and R. Hofman, “Intelligent video surveillance systems for public spaces–a survey,” Journal of Theoretical and Applied Computer Science, vol. 8(2014) no. 4, pp. 13–27.
M. Ye, J. Shen, G. Lin, T. Xiang, L. Shao, and S. C. H. Hoi, “Deep learning for person re-identification: A survey and outlook,” IEEE Trans. Pattern Anal. Mach. Intell.vol. 44(2022) pp. 2872–2893.
D. Wang and S. Zhang, “Unsupervised person re-identification via multilabel classification,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10 981–10 990.
Z. Dai, G. Wang, W. Yuan, S. Zhu, and P. Tan, “Cluster contrast for unsupervised person re-identification,” in Proceedings of the Asian Conference on Computer Vision, 2022, pp. 1142–1160.
Yang, H.-X. Yu, A. Wu, and W.-S. Zheng, “Patch-based discriminative feature learning for unsupervised person re-identification,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3633–3642.
Z. Zhang, C. Lan, W. Zeng, X. Jin, and Z. Chen, “Relation-aware global attention for person re-identification,” 2020, pp. 3186–3195.
H. Luo, Y. Gu, X. Liao, S. Lai, and W. Jiang, “Bag of tricks and a strong baseline for deep person re-identification,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 2019.
A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jegou, “Training data-efficient image transformers & distillation through attention,” in International conference on machine learning. PMLR, 2021, pp. 10347–10357.
X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable detr: Deformable transformers for end-to-end object detection,” arXiv preprint arXiv:2010.04159, 2020.
Z. Dai, G. Wang, W. Yuan, S. Zhu, and P. Tan, “Cluster contrast for unsupervised person re-identification,” in Proceedings of the Asian Conference on Computer Vision, 2022, pp. 1142–1160.
Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Learning to adapt invariance in memory for person re-identification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 8, pp. 2723–2738, 2020
K. Zheng, W. Liu, L. He, T. Mei, J. Luo, and Z. J. Zha, “Group-aware label transfer for domain adaptive person re-identification,” pp. 5306– 5315, 2021
Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Invariance matters: Exemplar memory for domain adaptive person re-identification,” 2019, pp. 598–607.
Y. Dai, J. Liu, Y. Sun, Z. Tong, C. Zhang, and L.-Y. Duan, “IDM: An intermediate domain module for domain adaptive person reid,” 2021, pp. 11 844–11 854.
Y. Ge, F. Zhu, D. Chen, R. Zhao et al., “Self-paced contrastive learning with hybrid memory for domain adaptive object reid,” Advances in Neural Information Processing Systems, vol. 33, pp. 11 309–11 321, 2020.
H. Chen, B. Lagadec, and F. Bremond, “ICE: Inter-instance contrastive encoding for unsupervised person re-identification,” 2021, pp. 14960– 14969.
Y. Fu, Y. Wei, G. Wang, Y. Zhou, H. Shi, and T. S. Huang, “Selfsimilarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification,” 2019, pp. 6112–6121.
S. He, H. Luo, P. Wang, F. Wang, H. Li, and W. Jiang, “Transreid: Transformer-based object re-identification,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 15 013–15 022.
G. Zhang, P. Zhang, J. Qi, and H. Lu, “Hat: Hierarchical aggregation transformers for person re-identification,” in Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 516–525.
H. Luo, P. Wang, Y. Xu, F. Ding, Y. Zhou, F. Wang, H. Li, and R. Jin, “Self-supervised pre-training for transformer-based person reidentification,” arXiv preprint arXiv:2111.12084, 2021.
