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
Neste artigo, propomos uma função de perda tripla semissupervisionada que realiza o aprendizado de representação semissupervisionado de uma maneira nova. Estendemos a perda tripla convencional, que usa dados rotulados para obter aprendizado de representação, para que possa lidar com dados não rotulados. Estimamos, antecipadamente, o grau em que cada rótulo se aplica a cada ponto de dados não rotulado e otimizamos a função de perda com recursos não rotulados de acordo com as proporções resultantes. Como a função de perda proposta tem o efeito de ajustar a distribuição de todos os dados não rotulados, ela complementa métodos baseados na regularização de consistência, que tem sido extensivamente estudado nos últimos anos. Combinado com um método baseado em regularização de consistência, nosso método alcança um aprendizado semissupervisionado mais preciso. Experimentos mostram que a função de perda proposta atinge uma precisão maior do que o método convencional de ajuste fino.
Kazuhiko MURASAKI
NTT
Shingo ANDO
NTT
Jun SHIMAMURA
NTT
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
Kazuhiko MURASAKI, Shingo ANDO, Jun SHIMAMURA, "Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 4, pp. 778-784, April 2022, doi: 10.1587/transinf.2021EDP7073.
Abstract: In this paper, we propose a semi-supervised triplet loss function that realizes semi-supervised representation learning in a novel manner. We extend conventional triplet loss, which uses labeled data to achieve representation learning, so that it can deal with unlabeled data. We estimate, in advance, the degree to which each label applies to each unlabeled data point, and optimize the loss function with unlabeled features according to the resulting ratios. Since the proposed loss function has the effect of adjusting the distribution of all unlabeled data, it complements methods based on consistency regularization, which has been extensively studied in recent years. Combined with a consistency regularization-based method, our method achieves more accurate semi-supervised learning. Experiments show that the proposed loss function achieves a higher accuracy than the conventional fine-tuning method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7073/_p
Copiar
@ARTICLE{e105-d_4_778,
author={Kazuhiko MURASAKI, Shingo ANDO, Jun SHIMAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data},
year={2022},
volume={E105-D},
number={4},
pages={778-784},
abstract={In this paper, we propose a semi-supervised triplet loss function that realizes semi-supervised representation learning in a novel manner. We extend conventional triplet loss, which uses labeled data to achieve representation learning, so that it can deal with unlabeled data. We estimate, in advance, the degree to which each label applies to each unlabeled data point, and optimize the loss function with unlabeled features according to the resulting ratios. Since the proposed loss function has the effect of adjusting the distribution of all unlabeled data, it complements methods based on consistency regularization, which has been extensively studied in recent years. Combined with a consistency regularization-based method, our method achieves more accurate semi-supervised learning. Experiments show that the proposed loss function achieves a higher accuracy than the conventional fine-tuning method.},
keywords={},
doi={10.1587/transinf.2021EDP7073},
ISSN={1745-1361},
month={April},}
Copiar
TY - JOUR
TI - Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data
T2 - IEICE TRANSACTIONS on Information
SP - 778
EP - 784
AU - Kazuhiko MURASAKI
AU - Shingo ANDO
AU - Jun SHIMAMURA
PY - 2022
DO - 10.1587/transinf.2021EDP7073
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2022
AB - In this paper, we propose a semi-supervised triplet loss function that realizes semi-supervised representation learning in a novel manner. We extend conventional triplet loss, which uses labeled data to achieve representation learning, so that it can deal with unlabeled data. We estimate, in advance, the degree to which each label applies to each unlabeled data point, and optimize the loss function with unlabeled features according to the resulting ratios. Since the proposed loss function has the effect of adjusting the distribution of all unlabeled data, it complements methods based on consistency regularization, which has been extensively studied in recent years. Combined with a consistency regularization-based method, our method achieves more accurate semi-supervised learning. Experiments show that the proposed loss function achieves a higher accuracy than the conventional fine-tuning method.
ER -