|
 
|
[LLC19] From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
Conférence Internationale avec comité de lecture : 23rd International Conference on Multimedia Modeling, January 2019, Vol. 11296, pp.1-13, Series LNCS, Thessaloniki, Grece, (DOI: 10.1007/978-3-030-05716-9_38)
motcle:
Résumé:
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes. It relies on additional semantic knowledge for which a mapping can be learned with training examples of seen classes. While classical ZSL considers the recognition performance on unseen classes only, generalized zero-shot learning (GZSL) aims at maximizing performance on both seen and unseen classes. In this paper, we propose a new process for training and evaluation in the GZSL setting; this process addresses the gap in performance between samples from unseen and seen classes by penalizing the latter, and enables to electhyper-parameters well-suited to the GZSL task. It can be applied to any existing ZSL approach and leads to a significant performance boost: the experimental evaluation shows that GZSL performance, averaged over eight state-of-the-art methods, is improved from 28.5 to 42.2 on CUB and from 28.2 to 57.1 on AwA2.
Collaboration:
CEA
BibTeX
| @inproceedings { | |||
| LLC19, | |||
| title | = | "{From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process}", | |
| author | = | " Y. Le Cacheux and H. Le Borgne and M. Crucianu ", | |
| booktitle | = | "{23rd International Conference on Multimedia Modeling}", | |
| year | = | 2019, | |
| edition | = | "Springer", | |
| month | = | "January", | |
| series | = | "LNCS", | |
| volume | = | 11296, | |
| pages | = | "1-13", | |
| address | = | "Thessaloniki, Grece", | |
| doi | = | "10.1007/978-3-030-05716-9_38", | |
| } | |||
