The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Uma estrutura baseada em perda tripla para aprendizagem generalizada de tiro zero é apresentada nesta carta. A abordagem aprende um espaço latente compartilhado para recursos e atributos de imagem usando autoencoders variacionais alinhados e variantes de perda tripla. Então treinamos um classificador no espaço latente. Os resultados experimentais demonstram que a estrutura proposta alcança grandes melhorias.
Yaying SHEN
Nanjing University of Posts and Telecommunications
Qun LI
Nanjing University of Posts and Telecommunications
Ding XU
Nanjing University of Posts and Telecommunications
Ziyi ZHANG
Nanjing University of Posts and Telecommunications
Rui YANG
Nanjing University of Posts and Telecommunications
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Yaying SHEN, Qun LI, Ding XU, Ziyi ZHANG, Rui YANG, "Triple Loss Based Framework for Generalized Zero-Shot Learning" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 4, pp. 832-835, April 2022, doi: 10.1587/transinf.2021EDL8079.
Abstract: A triple loss based framework for generalized zero-shot learning is presented in this letter. The approach learns a shared latent space for image features and attributes by using aligned variational autoencoders and variants of triplet loss. Then we train a classifier in the latent space. The experimental results demonstrate that the proposed framework achieves great improvement.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8079/_p
Copiar
@ARTICLE{e105-d_4_832,
author={Yaying SHEN, Qun LI, Ding XU, Ziyi ZHANG, Rui YANG, },
journal={IEICE TRANSACTIONS on Information},
title={Triple Loss Based Framework for Generalized Zero-Shot Learning},
year={2022},
volume={E105-D},
number={4},
pages={832-835},
abstract={A triple loss based framework for generalized zero-shot learning is presented in this letter. The approach learns a shared latent space for image features and attributes by using aligned variational autoencoders and variants of triplet loss. Then we train a classifier in the latent space. The experimental results demonstrate that the proposed framework achieves great improvement.},
keywords={},
doi={10.1587/transinf.2021EDL8079},
ISSN={1745-1361},
month={April},}
Copiar
TY - JOUR
TI - Triple Loss Based Framework for Generalized Zero-Shot Learning
T2 - IEICE TRANSACTIONS on Information
SP - 832
EP - 835
AU - Yaying SHEN
AU - Qun LI
AU - Ding XU
AU - Ziyi ZHANG
AU - Rui YANG
PY - 2022
DO - 10.1587/transinf.2021EDL8079
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2022
AB - A triple loss based framework for generalized zero-shot learning is presented in this letter. The approach learns a shared latent space for image features and attributes by using aligned variational autoencoders and variants of triplet loss. Then we train a classifier in the latent space. The experimental results demonstrate that the proposed framework achieves great improvement.
ER -