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
A tarefa de anotação de imagens está se tornando extremamente importante para a recuperação eficiente de imagens da web e de outros grandes bancos de dados. No entanto, a enorme informação semântica e a dependência complexa dos rótulos de uma imagem tornam a tarefa um desafio. Portanto, determinar a semelhança semântica entre vários rótulos em uma imagem é útil para entender qualquer atribuição de rótulo incompleta para recuperação de imagem. Este trabalho propõe um novo método para resolver o problema de anotação de imagens multi-rótulos, unificando dois tipos diferentes de termos de regularização laplaciana em redes neurais convolucionais profundas (CNN) para desempenho robusto de anotação. O modelo unificado de regularização Laplaciana é implementado para abordar os rótulos ausentes de forma eficiente, gerando a similaridade contextual entre os rótulos tanto interna quanto externamente por meio de suas semelhanças semânticas, que é a principal contribuição deste estudo. Especificamente, geramos matrizes de similaridade entre rótulos internamente usando o método de quantificação tipo III de Hayashi e externamente usando o método word2vec. As matrizes de similaridade geradas pelos dois métodos diferentes são então combinadas como um termo de regularização Laplaciana, que é usado como a nova função objetivo da CNN profunda. O termo Regularização implementado neste estudo é capaz de resolver o problema de anotação multirótulo, possibilitando uma rede neural treinada de forma mais eficaz. Resultados experimentais em conjuntos de dados de benchmark públicos revelam que o modelo de regularização unificado proposto com CNN profunda produz resultados significativamente melhores do que a CNN de linha de base sem regularização e outros métodos de última geração para prever rótulos ausentes.
Jonathan MOJOO
Hiroshima University
Yu ZHAO
Hiroshima University
Muthu Subash KAVITHA
Hiroshima University
Junichi MIYAO
Hiroshima University
Takio KURITA
Hiroshima 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.
Copiar
Jonathan MOJOO, Yu ZHAO, Muthu Subash KAVITHA, Junichi MIYAO, Takio KURITA, "Completion of Missing Labels for Multi-Label Annotation by a Unified Graph Laplacian Regularization" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 10, pp. 2154-2161, October 2020, doi: 10.1587/transinf.2019EDP7318.
Abstract: The task of image annotation is becoming enormously important for efficient image retrieval from the web and other large databases. However, huge semantic information and complex dependency of labels on an image make the task challenging. Hence determining the semantic similarity between multiple labels on an image is useful to understand any incomplete label assignment for image retrieval. This work proposes a novel method to solve the problem of multi-label image annotation by unifying two different types of Laplacian regularization terms in deep convolutional neural network (CNN) for robust annotation performance. The unified Laplacian regularization model is implemented to address the missing labels efficiently by generating the contextual similarity between labels both internally and externally through their semantic similarities, which is the main contribution of this study. Specifically, we generate similarity matrices between labels internally by using Hayashi's quantification method-type III and externally by using the word2vec method. The generated similarity matrices from the two different methods are then combined as a Laplacian regularization term, which is used as the new objective function of the deep CNN. The Regularization term implemented in this study is able to address the multi-label annotation problem, enabling a more effectively trained neural network. Experimental results on public benchmark datasets reveal that the proposed unified regularization model with deep CNN produces significantly better results than the baseline CNN without regularization and other state-of-the-art methods for predicting missing labels.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7318/_p
Copiar
@ARTICLE{e103-d_10_2154,
author={Jonathan MOJOO, Yu ZHAO, Muthu Subash KAVITHA, Junichi MIYAO, Takio KURITA, },
journal={IEICE TRANSACTIONS on Information},
title={Completion of Missing Labels for Multi-Label Annotation by a Unified Graph Laplacian Regularization},
year={2020},
volume={E103-D},
number={10},
pages={2154-2161},
abstract={The task of image annotation is becoming enormously important for efficient image retrieval from the web and other large databases. However, huge semantic information and complex dependency of labels on an image make the task challenging. Hence determining the semantic similarity between multiple labels on an image is useful to understand any incomplete label assignment for image retrieval. This work proposes a novel method to solve the problem of multi-label image annotation by unifying two different types of Laplacian regularization terms in deep convolutional neural network (CNN) for robust annotation performance. The unified Laplacian regularization model is implemented to address the missing labels efficiently by generating the contextual similarity between labels both internally and externally through their semantic similarities, which is the main contribution of this study. Specifically, we generate similarity matrices between labels internally by using Hayashi's quantification method-type III and externally by using the word2vec method. The generated similarity matrices from the two different methods are then combined as a Laplacian regularization term, which is used as the new objective function of the deep CNN. The Regularization term implemented in this study is able to address the multi-label annotation problem, enabling a more effectively trained neural network. Experimental results on public benchmark datasets reveal that the proposed unified regularization model with deep CNN produces significantly better results than the baseline CNN without regularization and other state-of-the-art methods for predicting missing labels.},
keywords={},
doi={10.1587/transinf.2019EDP7318},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - Completion of Missing Labels for Multi-Label Annotation by a Unified Graph Laplacian Regularization
T2 - IEICE TRANSACTIONS on Information
SP - 2154
EP - 2161
AU - Jonathan MOJOO
AU - Yu ZHAO
AU - Muthu Subash KAVITHA
AU - Junichi MIYAO
AU - Takio KURITA
PY - 2020
DO - 10.1587/transinf.2019EDP7318
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2020
AB - The task of image annotation is becoming enormously important for efficient image retrieval from the web and other large databases. However, huge semantic information and complex dependency of labels on an image make the task challenging. Hence determining the semantic similarity between multiple labels on an image is useful to understand any incomplete label assignment for image retrieval. This work proposes a novel method to solve the problem of multi-label image annotation by unifying two different types of Laplacian regularization terms in deep convolutional neural network (CNN) for robust annotation performance. The unified Laplacian regularization model is implemented to address the missing labels efficiently by generating the contextual similarity between labels both internally and externally through their semantic similarities, which is the main contribution of this study. Specifically, we generate similarity matrices between labels internally by using Hayashi's quantification method-type III and externally by using the word2vec method. The generated similarity matrices from the two different methods are then combined as a Laplacian regularization term, which is used as the new objective function of the deep CNN. The Regularization term implemented in this study is able to address the multi-label annotation problem, enabling a more effectively trained neural network. Experimental results on public benchmark datasets reveal that the proposed unified regularization model with deep CNN produces significantly better results than the baseline CNN without regularization and other state-of-the-art methods for predicting missing labels.
ER -