Abstract
Relative attributes can serve as a very useful method for zero-shot learning of images. This was shown by the work of Parikh and Grauman [1] where an image is expressed in terms of attributes that are relatively specified between different class pairs. However, for zero-shot learning the authors had assumed a simple Gaussian Mixture Model (GMM) that used the GMM based clustering to obtain the label for an unknown target test example. In this paper, we contribute a principled approach that uses Gaussian Process based classification to obtain the posterior probability for each sample of an unknown target class, in terms of Gaussian process classification and regression for nearest sample images. We analyse different variants of this approach and show that such a principled approach yields improved performance and a better understanding in terms of probabilistic estimates. The method is evaluated on standard Pubfig and Shoes with Attributes benchmarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Parikh, D., Grauman, K., Metaxas, D.N., Quan, L., Sanfeliu, A., Van Gool, L.J.: In: Proceedings of International Conference on Computer Vision (ICCV), pp. 503–510. IEEE Computer Society (2011)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006)
Biswas, A., Parikh, D.: Simultaneous active learning of classifiers and attributes via relative feedback. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)
Berg, T.L., Berg, A.C., Shih, J.: Automatic attribute discovery and characterization from noisy web data. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 663–676. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15549-9_48
Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between class attribute transfer. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2009)
Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453–465 (2014)
Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for attribute-based classification. In: Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013, pp. 819–826 (2013)
Jayaraman, D., Grauman, K.: Zero-shot learning with unreliable attributes. In: NIPS (2014)
Yu, A., Grauman, K.: Just noticeable differences in visual attributes. In: International Conference on Computer Vision (ICCV), December 2015
Elhoseiny, M., Saleh, B., Elgammal, A.: Write a classifier: zero-shot learning using purely textual descriptions. In: IEEE International Conference on Computer Vision (ICCV), December 2013
Zhao, X., Kersting, K., Tresp, V.: Multi-relational learning with Gaussian processes. In: Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI), Pasadena, California, USA, 11–17 July 2009, pp. 1309–1314 (2009)
Rodner, E., Denzler, J.: One-shot learning of object categories using dependent Gaussian processes. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) DAGM 2010. LNCS, vol. 6376, pp. 232–241. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15986-2_24
Rasmussen, C.E., Nickisch, H.: Gaussian processes for machine learning (GPML) toolbox. J. Mach. Learn. Res. 11, 3011–3015 (2010)
Zhen-Yong, F., Xiang, T.A., Kodirov, E., Gong, S.: Zero-shot object recognition by semantic manifold distance. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), Boston, MA, USA, 7–12 June 2015, pp. 2635–2644 (2015)
Mensink, T.E.J., Gavves, E., Snoek, C.G.M.: COSTA: co-occurrence statistics for zero-shot classification. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Dolma, Y., Namboodiri, V.P. (2017). Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes. In: Lai, SH., Lepetit, V., Nishino, K., Sato, Y. (eds) Computer Vision – ACCV 2016. ACCV 2016. Lecture Notes in Computer Science(), vol 10115. Springer, Cham. https://doi.org/10.1007/978-3-319-54193-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-54193-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54192-1
Online ISBN: 978-3-319-54193-8
eBook Packages: Computer ScienceComputer Science (R0)