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
웹 및 기타 대규모 데이터베이스에서 효율적인 이미지 검색을 위해 이미지 주석 작업이 엄청나게 중요해지고 있습니다. 그러나 막대한 의미 정보와 이미지에 대한 레이블의 복잡한 종속성은 작업을 어렵게 만듭니다. 따라서 이미지의 여러 레이블 간의 의미적 유사성을 결정하는 것은 이미지 검색을 위한 불완전한 레이블 할당을 이해하는 데 유용합니다. 이 연구에서는 강력한 주석 성능을 위해 심층 합성곱 신경망(CNN)에서 두 가지 유형의 라플라시안 정규화 용어를 통합하여 다중 레이블 이미지 주석 문제를 해결하는 새로운 방법을 제안합니다. 통합 라플라시안 정규화 모델은 본 연구의 주요 기여인 의미론적 유사성을 통해 내부 및 외부 레이블 간의 문맥적 유사성을 생성함으로써 누락된 레이블을 효율적으로 해결하기 위해 구현됩니다. 구체적으로 내부적으로는 Hayashi의 정량화 방법-유형 III을 사용하여 레이블 간의 유사성 행렬을 생성하고 외부에서는 word2vec 방법을 사용하여 레이블 간의 유사성 행렬을 생성합니다. 두 가지 다른 방법에서 생성된 유사성 행렬은 Laplacian 정규화 용어로 결합되며 이는 심층 CNN의 새로운 목적 함수로 사용됩니다. 본 연구에서 구현된 정규화 용어는 다중 레이블 주석 문제를 해결할 수 있어 보다 효과적으로 훈련된 신경망을 가능하게 합니다. 공개 벤치마크 데이터 세트에 대한 실험 결과에 따르면 심층 CNN을 사용하여 제안된 통합 정규화 모델은 정규화 및 누락된 레이블을 예측하기 위한 기타 최첨단 방법이 없는 기본 CNN보다 훨씬 더 나은 결과를 생성하는 것으로 나타났습니다.
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.
부
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
부
@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},}
부
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 -