Loading...

An attribute learning method for zero-shot recognition

Yazdanian, R ; Sharif University of Technology

676 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianCEE.2017.7985434
  3. Abstract:
  4. Recently, the problem of integrating side information about classes has emerged in the learning settings like zero-shot learning. Although using multiple sources of information about the input space has been investigated in the last decade and many multi-view and multi-modal learning methods have already been introduced, the attribute learning for classes (output space) is a new problem that has been attended in the last few years. In this paper, we propose an attribute learning method that can use different sources of descriptions for classes to find new attributes that are more proper to be used as class signatures. Experimental results show that the learned attributes by the proposed method can improve the accuracy of the state-of-the-art zero-shot learning methods. © 2017 IEEE
  5. Keywords:
  6. Covariance matrix ; Unsupervised learning ; Attribute learning ; Learning methods ; Learning settings ; Multi-modal learning ; Multiple source ; Side information ; State of the art ; Zero-Shot learning ; Learning systems
  7. Source: 2017 25th Iranian Conference on Electrical Engineering, ICEE 2017, 2 May 2017 through 4 May 2017 ; 2017 , Pages 2235-2240 ; 9781509059638 (ISBN)
  8. URL: https://ieeexplore.ieee.org/document/7985434