Open AccessZero‐shot learning by exploiting class‐related and attribute‐related prior knowledge
Author(s) -
Wang Xuesong,
Chen Chen,
Cheng Yuhu
Publication year - 2016
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2015.0131
Subject(s) - artificial intelligence , computer science , class (philosophy) , pattern recognition (psychology) , pascal (unit) , cosine similarity , machine learning , correlation , attribute domain , shot (pellet) , data mining , mathematics , rough set , chemistry , geometry , organic chemistry , programming language
The existing attribute‐based zero‐shot learning models at different levels ignore some necessary prior knowledge. It is essential to improve classification accuracy of zero‐shot learning that how to mine attribute‐related and class‐related prior knowledge further being incorporated into the attribute prediction models. For the mining of class‐related prior knowledge, measurement of the class–class correlation by using whitened cosine similarity is proposed. Likewise for the mining of attribute‐related prior knowledge, measurements of the attribute–class and attribute–attribute correlation are proposed by using sparse representation coefficient. Therefore, a novel indirect attribute prediction (IAP) model is presented by exploiting class‐related and attribute‐related prior knowledge (IAP_CAPK). Experimental results on animals with attributes and a‐Pascal/a‐Yahoo datasets show that, when compared with IAP and direct attribute prediction, the proposed IAP_CAPK not only yields more accurate attribute prediction and zero‐shot image classification, but also achieves much higher computational efficiency.