Attribute relaxation from class level to instance level for zero-shot learning

Attribute relaxation from class level to instance level for zero-shot learning

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

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(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
Your details
Why are you recommending this title?
Select reason:
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Conventional zero-shot learning (ZSL) methods usually use class-level attribute, which corresponds to a batch of images of same category. This setting is not reasonable since the images even though belong to same category still have variances in their attribute items. To alleviate this phenomenon, the authors propose a novel method namely attribute relaxation (AR) to extend attributes from class level to instance level by adding a small variance matrix, which is more reasonable than traditional ZSL methods such as Semantic AutoEncoder that projects features from multi to one. Extensive experiments on four popular datasets show that AR can significantly improve the method using only class-level attributes, and verifies that AR can make the projected features in attribute space more discriminative.


    1. 1)
      • 1. Kodirov, E., Xiang, T., Gong, S.: ‘Semantic autoencoder for zero-shot learning’. Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, July 2017.
    2. 2)
      • 2. Long, Y., Shao, L.: ‘Attribute embedding with visual-semantic ambiguity removal for zero-shot learning’. British Machine Vision Conf. (BMVC), York, UK, September 2016.
    3. 3)
      • 3. Zhang, H., Long, Y., Shao, L.: ‘Zero-shot hashing with orthogonal projection for image retrieval’, Pattern Recog. Lett., 2018, Available at
    4. 4)
      • 4. Yang, Y., Chen, W., Luo, Y., et al: ‘Zero-shot hashing via transferring supervised knowledge’. ACM Multimedia, Amsterdam, The Netherlands, October 2016.
    5. 5)
    6. 6)
      • 6. Patterson, G., Hays, J.: ‘Sun attribute database: discovering, annotating, and recognizing scene attributes’. Conf. Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012.
    7. 7)
      • 7. Welinder, P., Branson, S., Mita, T., et al: ‘Caltech-UCSD Birds 200’. Technical Report CNS-TR-2010-001, Caltech, 2010.
    8. 8)
    9. 9)
      • 9. Farhadi, A., Endres, I., Hoiem, D., et al: ‘Describing objects by their attributes’. Conf. Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, June 2009.
    10. 10)
      • 10. Xian, Y., Lampert, C., Schiele, B., et al: ‘Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly’, Trans. Pattern Anal. Mach. Intell, 2017, DOI: 10.1109/TPAMI.2018.2857768.
    11. 11)
      • 11. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, CA, USA, 26 June–1 July 2016, 2016.
    12. 12)
      • 12. Maaten, L., Hinton, G.: ‘Visualizing high-dimensional data using t-SNE’, J. Mach. Learn. Res., 2008, 9, (11), pp. 25792605.

Related content

This is a required field
Please enter a valid email address