Zero-shot Learning (ZSL) aims to predict for those classes that havenever appeared in the training data . The key of implementing ZSL is to leverage the prior knowledge of classes which buildsthe semantic relationship between classes and enables the transfer of the learned models (e.g., features) from training classes (i.e., seen classes) tounseen classes) to ZSL . The study found that the ontology-based class semantics outperform the previous priors e.g. by an average of 12.4 accuracy points in the standard ZSL across two example datasets . In this paper, we explore richerand more competitive prior knowledge to model the inter-class relationship forZSL via .ZSL, where our method often achieves better performance than the state-of-the-art models. In particular, on four representative ZSL baselines ofIMGC, the . method often achieve better performance . Our method often .

Author(s) : Yuxia Geng, Jiaoyan Chen, Zhuo Chen, Jeff Z. Pan, Zhiquan Ye, Zonggang Yuan, Yantao Jia, Huajun Chen

Links : PDF - Abstract

Code :
Coursera

Keywords : classes - zsl - method - class - performance -

Leave a Reply

Your email address will not be published. Required fields are marked *