Generalized zero-shot learning is a significant topic but faced with bias problem, which leads to unseen classes being easily misclassified into seen classes. Hence we propose a embedding model called co-representation network to learn a more uniform visual embedding space that effectively alleviates the bias problem and helps with classification. We mathematically analyze our model and find it learns a projection with high local linearity, which is proved to cause less bias problem. The network consists of a cooperation module for representation and a relation module for classification, it is simple in structure and can be easily trained in an end-to-end manner. Experiments show that our method outperforms existing generalized zero-shot learning methods on several benchmark datasets.
Fei Zhang (Xidian University)
Guangming Shi (Xidian University)
Related Events (a corresponding poster, oral, or spotlight)
2019 Poster: Co-Representation Network for Generalized Zero-Shot Learning »
Wed Jun 12th 01:30 -- 04:00 AM Room Pacific Ballroom