Synonyms
Related Concepts
Definition
The goal of zero-shot learning is to construct a classifier that can identify object classes for which no training examples are available. When training data for some of the object classes is available but not for others, the name generalized zero-shot learning is commonly used.
In a wider sense, the phrase zero-shot is also used to describe other machine learning-based approaches that require no training data from the problem of interest, such as zero-shot action recognition or zero-shot machine translation.
Background
Object recognition systems are typically created by training a supervised machine learning model, such as a convolutional network. For this, a training set is required that consists of annotated images of all object classes of interest. When no annotated images of the target classes are available, the supervised approach is not applicable. Instead, classifiers...
This is a preview of subscription content, log in via an institution to check access.
References
Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes. In: Conference on computer vision and pattern recognition (CVPR), pp 1778–1785
Lampert CH, Nickisch H, Harmeling S (2014) Attribute-based classification for zero-shot visual object categorization. IEEE Trans Pattern Anal Mach Intell 36(3):453–465
Palatucci M, Pomerleau D, Hinton GE, Mitchell TM (2009) Zero-shot learning with semantic output codes. In: Conference on neural information processing systems (NIPS), pp 1410–1418
Elhoseiny M, Saleh B, Elgammal A (2013) Write a classifier: zero-shot learning using purely textual descriptions. In: International conference on computer vision (ICCV), pp 2584–2591
Socher R, Ganjoo M, Manning CD, Ng A (2013) Zero-shot learning through cross-modal transfer. In: Conference on neural information processing systems (NIPS), pp 935–943
Akata Z, Perronnin F, Harchaoui Z, Schmid C (2016) Label-embedding for image classification. IEEE Trans Pattern Anal Mach Intell 38(7):1425–1438
Akata Z, Reed S, Walter D, Lee H, Schiele B (2015) Evaluation of output embeddings for fine-grained image classification. In: Conference on computer vision and pattern recognition (CVPR), pp 2927–2936
Frome A, Corrado GS, Shlens J, Bengio S, Dean J, Ronzato M, Mikolov T (2013) Devise: a deep visual-semantic embedding model. In: Conference on neural information processing systems (NIPS), pp 2121–2129
Mensink T, Verbeek J, Perronnin F, Csurka G (2012) Metric learning for large scale image classification: generalizing to new classes at near-zero cost. In: European conference on computer vision. Springer, pp 488–501
Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B (2016) Latent embeddings for zero-shot classification. In: Conference on computer vision and pattern recognition (CVPR), pp 69–77
Xian Y, Lampert CH, Schiele B, Akata Z (2019) Zero-shot learning – a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans Pattern Anal Mach Intell (T-PAMI) 41(9):2251–2265
Johnson M, Schuster M, Le QV, Krikun M, Wu Y, Chen Z, Thorat N, Viégas F, Wattenberg M, Corrado G et al (2017) Google’s multilingual neural machine translation system: Enabling zero-shot translation. Trans Assoc Comput Linguist 5:339–351
Li J, Jing M, Lu K, Zhu L, Yang Y, Huang Z (2019) From zero-shot learning to cold-start recommendation. In: Conference on artificial intelligence (AAAI)
Author information
Authors and Affiliations
Corresponding author
Section Editor information
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this entry
Cite this entry
Lampert, C.H. (2020). Zero-Shot Learning. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_874-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03243-2_874-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03243-2
Online ISBN: 978-3-030-03243-2
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering