Generalizable and efficient cross‐domain person re‐identification model using deep metric learning
Abstract
Most of the successful person re‐ID models conduct supervised training and need a large number of training data. These models fail to generalise well on unseen unlabelled testing sets. The authors aim to learn a generalisable person re‐identification model. The model uses one labelled source dataset and one unlabelled target dataset during training and generalises well on the target testing set. To this end, after a feature extraction by the ResNext‐50 network, the authors optimise the model by three loss functions. (a) One loss function is designed to learn the features of the target domain by tuning the distances between target images. Therefore, the trained model will be more robust to overcome the intra‐domain variations in the target domain and generalises well on the target testing set. (b) One triplet loss is used which considers both source and target domains and makes the model learn the inter‐domain variations between source and target domain as well as the variations in the target domain. (c) Also, one loss function is for supervised learning on the labelled source domain. Extensive experiments on Market1501 and DukeMTMC re‐ID show that the model achieves a very competitive performance compared with state‐of‐the‐art models and also it requires an acceptable amount of GPU RAM compared to other successful models.
Graphical Abstract
In this work, the authors aim to learn a generalisable person re‐identification model. The model uses one labelled source dataset and one unlabelled target dataset during training and generalises well on the target testing set. To this end, after a feature extraction by the ResNext‐50 network, the authors optimise our model by three loss functions.
References
[1]
Wang, X., et al.: Exploiting global camera network constraints for unsupervised video person re‐identification. IEEE Trans. Circ. Syst. Video Technol. 31(10), 4020–4030 (2020). https://doi.org/10.1109/tcsvt.2020.3043444
[2]
Zheng, L., et al.: Scalable person re‐identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)
[3]
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re‐identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3754–3762 (2017)
[4]
Li, W., et al.: Deepreid: deep filter pairing neural network for person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152–159 (2014)
[5]
Bromley, J., et al.: Signature verification using a “siamese” time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(04), 669–688 (1993). https://doi.org/10.1142/s0218001493000339
[6]
Xie, S., et al.: Aggregated residual transfor‐mations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
[7]
Huang, T., Russell, S.: Object identification in a bayesian context. IJCAI 97, 1276–1282 (1997)
[8]
Zajdel, W., Zivkovic, Z., Krose, B.J.: Keeping track of humans: have i seen this person before? In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, pp. 2081–2086. IEEE (2005)
[9]
Gheissari, N., Sebastian, T.B., Hartley, R.: Person reidentification using spatiotemporal appearance. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2, pp. 1528–1535. IEEE (2006)
[10]
Yi, D., et al.: Deep metric learning for person re‐identification. In: 2014 22nd International Conference on Pattern Recogni‐Tion, pp. 34–39. IEEE (2014)
[11]
Ni, X., Fang, L., Huttunen, H.: Adaptivereid: Adaptive l2 Regularization in Person Re‐identification. arXiv preprint arXiv:2007.07875
[12]
Wang, G., et al.: Spatial‐temporal person re‐identification. In: Proceedings of the AAAI Conference on Artificial in‐ Telligence, vol. 33, pp. 8933–8940 (2019)
[13]
Quan, R., et al.: Auto‐reid: searching for a part‐aware convnet for person re‐identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3750–3759 (2019)
[14]
Zheng, Z., et al.: Joint discriminative and generative learning for person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2138–2147 (2019)
[15]
Zhou, K., et al.: Omni‐scale feature learning for person re‐identification. In: Proceedings of the IEEE International Confer‐Ence on Computer Vision, pp. 3702–3712 (2019)
[16]
Sun, Y., et al.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision, pp. 480–496. ECCV) (2018)
[17]
Ye, M., et al.: Deep learn‐Ing for Person Re‐identification: A Survey and Outlook. arXiv preprint arXiv:2001.04193
[18]
Hermans, A., Beyer, L., Leibe, B.: In Defense of the Triplet loss for Person Re‐identification. arXiv preprint arXiv:1703.07737
[19]
Chen, W., et al.: Beyond triplet loss: a deep quadru‐plet network for person re‐identification. In: Proceedings of the IEEE Con‐Ference on Computer Vision and Pattern Recognition, pp. 403–412 (2017)
[20]
Kodirov, E., Xiang, T., Gong, S.: Dictionary learning with iterative laplacian regularisation for unsupervised person re‐identification. BMVC 3, 8 (2015)
[21]
Elyor, K., et al.: Person re‐identification by unsuper‐vised£ 1 graph learning. Computer Vision‐ECCV (2016)
[22]
Lin, Y., et al.: A bottom‐up clustering 500 approach to unsupervised person re‐identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8738–8745 (2019)
[23]
Yu, H.‐X., Wu, A., Zheng, W.‐S.: Cross‐view asymmetric metric learning for unsupervised person re‐identification. In: Proceedings of the IEEE Interna‐Tional Conference on Computer Vision, pp. 994–1002 (2017)
[24]
Wei, L., et al.: Person transfer gan to bridge domain gap for person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 79–88 (2018)
[25]
Deng, W., et al.: Image‐image domain adaptation with preserved self‐similarity and domain‐dissimilarity for per‐son re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 994–1003 (2018)
[26]
Lv, J., Wang, X.: Cross‐dataset person re‐identification using similarity pre‐served generative adversarial networks. In: International Conference on Knowledge Science, Engineering and Management, pp. 171–183. Springer (2018)
[27]
Lv, J., et al.: Unsupervised cross‐dataset person re‐identification by transfer learning of spatial‐temporal patterns. In: Proceed‐Ings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7948–7956 (2018)
[28]
Song, L., et al.: Unsu‐pervised domain adaptive re‐identification: theory and practice. Pattern Recogn. 102, 107173 (2020). https://doi.org/10.1016/j.patcog.2019.107173
[29]
Liu, J., et al.: Adaptive transfer network for cross‐domain person re‐identification. In: Proceedings of the IEEE Con‐Ference on Computer Vision and Pattern Recognition, pp. 7202–7211 (2019)
[30]
Zhong, Z., et al.: Invariance matters: exemplar memory for domain adaptive person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 598–607 (2019)
[31]
Ding, Y., et al.: Adaptive exploration for unsupervised person re‐identification, ACM Transactions on Multimedia Computing. Communications, and Applications (TOMM) 16(1), 1–19 (2020). https://doi.org/10.1145/3369393
[32]
Zhong, Z., et al.: Learning to adapt invari‐ance in memory for person re‐identification. IEEE Trans. Pattern Anal. Mach. Intell., 1 (2020). https://doi.org/10.1109/tpami.2020.2976933
[33]
Zhu, J.‐Y., et al.: Unpaired image‐to‐image trans‐lation using cycle‐consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
[34]
Huang, H., et al.: Eanet: Enhancing Alignment for Cross‐Domain Person Re‐identification. arXiv preprint arXiv:1812.11369
[35]
Varior, R.R., Haloi, M., Wang, G.: Gated siamese convolutional neural net‐work architecture for human re‐identification. In: European Conference on Computer Vision, pp. 791–808. Springer (2016)
[36]
Chung, D., Tahboub, K., Delp, E.J.: A two stream siamese convolutional neural network for person re‐identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1983–1991 (2017)
[37]
Zheng, M., et al.: Re‐identification with consis‐tent attentive siamese networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5735–5744 (2019)
[38]
Ge, Y., et al.: Fd‐gan: pose‐guided feature distilling gan for robust person re‐identification. In: Advances in Neural Information Processing Systems, pp. 1222–1233 (2018)
[39]
Zhong, Z., et al.: Random Erasing Data Aug‐Mentation, pp. 13001–13008. AAAI (2020)
[40]
Huang, Y., et al.: Multi‐pseudo reg‐ularized label for generated data in person re‐identification. IEEE Trans. Image Process. 28(3), 1391–1403 (2018). https://doi.org/10.1109/tip.2018.2874715
[41]
Gulrajani, I., et al.: Im‐proved training of wasserstein gans. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
[42]
Ma, L., et al.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, pp. 406–416 (2017)
[43]
Zhong, Z., et al.: Camera style adaptation for person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5157–5166 (2018)
[44]
Schroff, F., et al.: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
[45]
Liu, J., et al.: Pose transferrable person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4099–4108 (2018)
[46]
Song, J., et al.: Generalizable person re‐identification by domain‐invariant mapping network. In: Proceed‐Ings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 719–728 (2019)
[47]
Guo, Y., Cheung, N.‐M.: Efficient and deep person re‐identification using multi‐level similarity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2335–2344 (2018)
[48]
Zhong, Z., et al.: Generalizing a person retrieval model hetero‐and homogeneously. In: Proceedings of the European Conference on Computer Vision, pp. 172–188. ECCV) (2018)
[49]
Ristani, E., et al.: Performance mea‐sures and a data set for multi‐target, multi‐camera tracking. In: European Conference on Computer Vision, pp. 17–35. Springer (2016)
[50]
Deng, J., et al.: Imagenet: a large‐scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
[51]
Nair, V., Hinton, G.E.: Rectified linear Units Improve Restricted Boltzmann Machines. ICML (2010)
[52]
Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Train‐Ing by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167
[53]
Srivastava, N., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
[54]
He, K., et al.: Deep residual learning for image recog‐nition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
[55]
Zagoruyko, S., Komodakis, N.: Wide Residual Networks. arXiv preprint arXiv:1605.07146
[56]
Peng, P., et al.: Unsupervised cross‐dataset transfer learning for person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1306–1315 (2016)
[57]
Fan, H., et al.: Unsupervised person re‐identification: clustering and fine‐tuning, ACM transactions on multimedia computing. Communications, and Applications (TOMM) 14(4), 1–18 (2018). https://doi.org/10.1145/3243316
[58]
Wang, J., et al.: Transferable joint attribute‐identity deep learning for unsupervised person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2275–2284 (2018)
[59]
Zhong, Z., et al.: Camstyle: a novel data augmentation method for person re‐identification. IEEE Trans. Image Process. 28(3), 1176–1190 (2018). https://doi.org/10.1109/tip.2018.2874313
[60]
Li, Y.‐J., et al.: Adaptation and re‐identification network: an unsupervised deep transfer learning approach to person re‐identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 172–178 (2018)
[61]
Qi, L., et al.: A novel unsupervised camera‐aware domain adaptation framework for person re‐identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8080–8089 (2019)
[62]
Tan, M., Le, Q.V., Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv preprint arXiv:1905.11946
Index Terms
- Generalizable and efficient cross‐domain person re‐identification model using deep metric learning
Index terms have been assigned to the content through auto-classification.
Recommendations
Unsupervised Cross-domain Person re-Identification by Deep Clustering and Instance Learning
AICCC '21: Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing ConferenceCross-domain unsupervised person re-identification (Re-id) has become more and more popular due to cost of labeled images. However, because of the large differences between two different domains in lighting, background, and so on, cross-domain ...
Unsupervised cross-domain person re-identification by instance and distribution alignment
Highlights- A novel idea of exploring instance-wise localised source knowledge for unsupervised cross-domain person re-id.
AbstractMost existing person re-identification (re-id) methods assume supervised model training on a separate large set of training samples from the target domain. While performing well in the training domain, such trained models are seldom ...
Cross-Domain Semi-Supervised Learning Using Feature Formulation
Semi-Supervised Learning (SSL) traditionally makes use of unlabeled samples In this paper, sample and instance are interchangeable terms. by including them into the training set through an automated labeling process. Such a primitive Semi-Supervised ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© 2023 The Authors. IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
Publisher
John Wiley & Sons, Inc.
United States
Publication History
Published: 13 June 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 21 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in