Co-Representation Network for Generalized Zero-Shot Learning

Fei Zhang, Guangming Shi
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:7434-7443, 2019.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-zhang19l, title = {Co-Representation Network for Generalized Zero-Shot Learning}, author = {Zhang, Fei and Shi, Guangming}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {7434--7443}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/zhang19l/zhang19l.pdf}, url = {https://proceedings.mlr.press/v97/zhang19l.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Co-Representation Network for Generalized Zero-Shot Learning %A Fei Zhang %A Guangming Shi %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-zhang19l %I PMLR %P 7434--7443 %U https://proceedings.mlr.press/v97/zhang19l.html %V 97 %X 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.
APA
Zhang, F. & Shi, G.. (2019). Co-Representation Network for Generalized Zero-Shot Learning. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:7434-7443 Available from https://proceedings.mlr.press/v97/zhang19l.html.

Related Material