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
Cette Lettre propose un modèle d'auto-encodeur supervisé par similarité sémantique pour un apprentissage zéro-shot. Avec l'aide des vecteurs de similarité sémantique des classes visibles et invisibles et de la branche de classification, nos résultats expérimentaux sur deux ensembles de données sont 7.3 % et 4 % meilleurs que l'état de l'art sur l'apprentissage zéro-shot conventionnel en termes de moyenne. précision top-1.
Fengli SHEN
Zhejiang University
Zhe-Ming LU
Zhejiang University
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.
Copier
Fengli SHEN, Zhe-Ming LU, "A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1419-1422, June 2020, doi: 10.1587/transinf.2019EDL8176.
Abstract: This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8176/_p
Copier
@ARTICLE{e103-d_6_1419,
author={Fengli SHEN, Zhe-Ming LU, },
journal={IEICE TRANSACTIONS on Information},
title={A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning},
year={2020},
volume={E103-D},
number={6},
pages={1419-1422},
abstract={This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.},
keywords={},
doi={10.1587/transinf.2019EDL8176},
ISSN={1745-1361},
month={June},}
Copier
TY - JOUR
TI - A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1419
EP - 1422
AU - Fengli SHEN
AU - Zhe-Ming LU
PY - 2020
DO - 10.1587/transinf.2019EDL8176
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.
ER -