http://iet.metastore.ingenta.com
1887

Enhanced multi-dataset transfer learning method for unsupervised person re-identification using co-training strategy

Enhanced multi-dataset transfer learning method for unsupervised person re-identification using co-training strategy

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This study proposes progressive unsupervised co-learning for unsupervised person re-identification by introducing a co-training strategy in an iterative training process. The authors’ method adopts an iterative training process to improve transferred models by iterating among clustering, selection, exchange, and fine-tuning. To solve the problem of transferring representations learned from multiple source datasets, their method utilises multiple convolutional neural network (CNN) models trained on different labelled source datasets by feeding soft labels obtained by clustering on target dataset to each other. The enhanced model can learn more discriminative person representations than the single model trained on multiple datasets. Experimental results on two large-scale benchmark datasets (i.e. DukeMTMC-reID and Market-1501) demonstrate that their method can enhance transferred CNN models by using more source datasets and is competitive to the state-of-the-art methods.

References

    1. 1)
      • 1. Zheng, L., Yang, Y., Hauptmann, A.: ‘Person re-identification: past, present and future’, arXiv preprint, 2016, arXiv: 1610.02984.
    2. 2)
      • 2. Farenzena, M., Bazzani, L., Perina, A., et al: ‘Person re-identification by symmetry-driven accumulation of local features’. IEEE Int. Conf. Computer Vision and Pattern Recognition, San Francisco, CA, 2010, pp. 23602367.
    3. 3)
      • 3. Liu, X., Song, M., Tao, D., et al: ‘Semi-supervised coupled dictionary learning for person re-identification’. Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 35503557.
    4. 4)
      • 4. Zhao, R., Ouyang, W., Wang, X.: ‘Unsupervised salience learning for person re-identification’. Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, Portland, OR, 2013, pp. 35863593.
    5. 5)
      • 5. Krizhevsky, A., Sutskever, I., Hinton, G.: ‘Imagenet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems 25 (NIPS 2012), 2012, pp. 10971105.
    6. 6)
      • 6. Ren, S., He, K., Girshick, R., et al: ‘Faster R-CNN: towards real-time object detection with region proposal networks’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 39, (6), pp. 11371149.
    7. 7)
      • 7. Taigman, Y., Yang, M., Ranzato, M., et al: ‘Deepface: closing the gap to human-level performance in face verification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 17011708.
    8. 8)
      • 8. Ahmed, E., Jones, M., Marks, T.: ‘An improved deep learning architecture for person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Boston, MA, 2015, pp. 39083916.
    9. 9)
      • 9. Xiao, T., Li, H., Ouyang, W., et al: ‘Learning deep feature representations with domain guided dropout for person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, 2016, pp. 12491258.
    10. 10)
      • 10. Zheng, Z., Zheng, L., Yang, Y.: ‘A discriminatively learned CNN embedding for person re-identification’, arXiv preprint, 2016, arXiv: 1611.05666.
    11. 11)
      • 11. Geng, M., Wang, Y., Xiang, T., et al: ‘Deep transfer learning for person re-identification’, arXiv preprint, 2016, arXiv: 1611.05244.
    12. 12)
      • 12. Peng, P., Xiang, T., Wang, Y., et al: ‘Unsupervised cross-dataset transfer learning for person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, 2016, pp. 13061315.
    13. 13)
      • 13. Fan, H., Zheng, L., Yang, Y.: ‘Unsupervised person re-identification: clustering and fine-tuning’, arXiv preprint, 2017, arXiv: 1705.10444.
    14. 14)
      • 14. Blum, A., Mitchell, T.: ‘Combining labeled and unlabeled data with co-training’. Proc. of the 11th Annual Conf. on Computational Learning Theory, 1998, pp. 92100.
    15. 15)
      • 15. Xiao, T., Li, S., Wang, B., et al: ‘End-to-end deep learning for person search’, arXiv preprint, 2016, arXiv: 1604.02984.
    16. 16)
      • 16. Almazan, J., Gajic, B., Murray, N., et al: ‘Re-ID done right: towards good practices for person re-identification’, arXiv preprint, 2018, arXiv: 1801.05339.
    17. 17)
      • 17. Chen, W., Chen, X., Chen, J., et al: ‘A multi-task deep network for person re-identification’. Proc. of the 31st AAAI Conf. on Artificial Intelligence (AAAI-17), 2017, pp. 39883994.
    18. 18)
      • 18. Yu, H., Wu, A., Zheng, W.: ‘Cross-view asymmetric metric learning for unsupervised person re-identification’. IEEE Int. Conf. on Computer Vision, Venice, 2017, pp. 9941002.
    19. 19)
      • 19. Yang, X., Wang, M., Hong, R., et al: ‘Enhancing person re-identification in a self-trained subspace’, ACM Trans. Multimedia Comput. Commun. Appl., 2017, 13, (3), pp. 27:127:23.
    20. 20)
      • 20. Wang, J., Zhu, X., Gong, S., et al: ‘Transferable joint attribute-identity deep learning for unsupervised person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018.
    21. 21)
      • 21. Deng, W., Zheng, L., Kang, G., et al: ‘Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018.
    22. 22)
      • 22. Zhou, Z., Li, M.: ‘Semi-supervised learning by disagreement’, Knowl. Inf. Syst., 2010, 24, (3), pp. 415439.
    23. 23)
      • 23. Hong, Y., Zhu, W.: ‘Spatial co-training for semi-supervised image classification’, Pattern Recognit. Lett., 2015, 63, pp. 5965.
    24. 24)
      • 24. Bianco, S., Ciocca, G., Cusano, C.: ‘CURL: image classification using co-training and unsupervised representation learning’, Comput. Vis. Image Underst., 2016, 145, pp. 1529.
    25. 25)
      • 25. Zheng, Z., Zheng, L., Yang, Y.: ‘Unlabeled samples generated by GAN improve the person re-identification baseline in vitro’. IEEE Int. Conf. on Computer Vision, Venice, 2017, pp. 37743782.
    26. 26)
      • 26. Ristani, E., Solera, F., Zou, R., et al: ‘Performance measures and a data set for multi-target, multi-camera tracking’. European Conf. on Computer Vision workshop on Benchmarking Multi-Target Tracking, 2016.
    27. 27)
      • 27. Zheng, L., Shen, L., Tian, L., et al: ‘Scalable person re-identification: a benchmark’. IEEE Int. Conf. on Computer Vision, Santiago, 2015, pp. 11161124.
    28. 28)
      • 28. Li, W., Zhao, R., Xiao, T., et al: ‘Deepreid: deep filter pairing neural network for person re-identification’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 152159.
    29. 29)
      • 29. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, 2016, pp. 770778.
    30. 30)
      • 30. Ester, M., Kriegel, H.P., Xu, X.: ‘A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise’. Int. Conf. Knowledge Discovery and Data Mining, 1996, pp. 226231.
    31. 31)
      • 31. Liao, S., Hu, Y., Zhu, X., et al: ‘Person re-identification by local maximal occurrence representation and metric learning’. IEEE Int. Conf. Computer Vision and Pattern Recognition, Boston, MA, 2015, pp. 21972206.
    32. 32)
      • 32. Zhu, J., Park, T., Isola, P., et al: ‘Unpaired image-to-image translation using cycle-consistent adversarial networks’, pp. 22422251.
    33. 33)
      • 33. Pan, S., Yang, Q.: ‘A survey on transfer learning’, IEEE Trans. Knowl. Data Eng., 2010, 22, (10), pp. 13451359.
    34. 34)
      • 34. Zhou, Z., Li, M.: ‘Exploiting unlabelled data using three classifiers’, IEEE Trans. Knowl. Data Eng., 2005, 17, (11), pp. 15291541.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2018.5103
Loading

Related content

content/journals/10.1049/iet-cvi.2018.5103
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address