Publications -> Journal Papers

A Survey of Zero-Shot Learning: Settings, Methods, and Applications


Authors: W. Wang, V. W. Zheng, H. Yu, and C. Miao
Title: A Survey of Zero-Shot Learning: Settings, Methods, and Applications
Abstract: Most machine-learning methods focus on classifying instances whose classes have already been seen in training. In practice, many applications require classifying instances whose classes have not been seen previously. Zero-shot learning is a powerful and promising learning paradigm, in which the classes covered by training instances and the classes we aim to classify are disjoint. In this paper, we provide a comprehensive survey of zero-shot learning. First of all, we provide an overview of zero-shot learning. According to the data utilized in model optimization, we classify zero-shot learning into three learning settings. Second, we describe different semantic spaces adopted in existing zero-shot learning works. Third, we categorize existing zero-shot learning methods and introduce representative methods under each category. Fourth, we discuss different applications of zero-shot learning. Finally, we highlight promising future research directions of zero-shot learning.
Keywords: Computing methodologies; Transfer learning; Zero-shot learning survey
Journal Name: ACM Transactions on Intelligent Systems and Technology (TIST), vol. 10, no. 2
Publisher: ACM
Year: 2019
Accepted PDF File: A_Survey_of_Zero-Shot_Learning_Settings_Methods_and_Applications_accepted.pdf
Permanent Link: https://doi.org/10.1145/3293318
Reference: W. Wang, V. W. Zheng, H. Yu, and C. Miao, "A Survey of Zero-Shot Learning: Settings, Methods, and Applications," ACM Transactions on Intelligent Systems and Technology (TIST), vol. 10, no. 2, February 2019, Art. no. 13.
bibtex: 
@article {LILY-j63,
   author  = {Wang, Wei and Zheng, Vincent W. and Yu, Han and Miao, Chunyan},
   title   = {A Survey of Zero-Shot Learning: Settings, Methods, and Applications},
   journal  = {ACM Transactions on Intelligent Systems and Technology (TIST)},
   year  = {2019},
   month  = {February },
   volume  = {10},
   number  = {2},
   pages  = {Art. no. 13},
   publisher  = {ACM},
}