A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning

Fengli SHEN  Zhe-Ming LU  

IEICE TRANSACTIONS on Information and Systems   Vol.E103-D   No.6   pp.1419-1422
Publication Date: 2020/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDL8176
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
zero-shot learning,  autoencoder,  image classification,  

Full Text: PDF>>
Buy this Article

This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.