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
Recentemente, características locais computadas usando redes neurais convolucionais (CNNs) apresentam bom desempenho na recuperação de imagens. As características convolucionais locais obtidas pelas CNNs (características LC) são projetadas para serem invariantes à tradução, no entanto, são inerentemente sensíveis a perturbações de rotação. Isso leva a erros de julgamento nas tarefas de recuperação. Neste trabalho, nosso objetivo é aumentar a robustez dos recursos LC contra a rotação da imagem. Para fazer isso, conduzimos uma avaliação experimental completa de três estratégias anti-rotação candidatas (aumento de dados no modelo, aumento de recursos no modelo e aumento de recursos pós-modelo), em dois tipos de ataque de rotação (ataque de conjunto de dados e ataque de consulta). ). No procedimento de treinamento, implementamos um protocolo de aumento de dados e um método de aumento de rede. No procedimento de teste, desenvolvemos um método de extração de recursos convolucionais transformados locais (LTC) e o avaliamos em diferentes configurações de rede. Finalizamos uma série de boas práticas com suportes quantitativos constantes, que levam à melhor estratégia para computar características LC com alta invariância de rotação na recuperação de imagens.
Longjiao ZHAO
Nagoya University
Yu WANG
Ritsumeikan University
Jien KATO
Ritsumeikan 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
Longjiao ZHAO, Yu WANG, Jien KATO, "Rethinking the Rotation Invariance of Local Convolutional Features for Content-Based Image Retrieval" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 1, pp. 174-182, January 2021, doi: 10.1587/transinf.2020EDP7017.
Abstract: Recently, local features computed using convolutional neural networks (CNNs) show good performance to image retrieval. The local convolutional features obtained by the CNNs (LC features) are designed to be translation invariant, however, they are inherently sensitive to rotation perturbations. This leads to miss-judgements in retrieval tasks. In this work, our objective is to enhance the robustness of LC features against image rotation. To do this, we conduct a thorough experimental evaluation of three candidate anti-rotation strategies (in-model data augmentation, in-model feature augmentation, and post-model feature augmentation), over two kinds of rotation attack (dataset attack and query attack). In the training procedure, we implement a data augmentation protocol and network augmentation method. In the test procedure, we develop a local transformed convolutional (LTC) feature extraction method, and evaluate it over different network configurations. We end up a series of good practices with steady quantitative supports, which lead to the best strategy for computing LC features with high rotation invariance in image retrieval.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7017/_p
Copiar
@ARTICLE{e104-d_1_174,
author={Longjiao ZHAO, Yu WANG, Jien KATO, },
journal={IEICE TRANSACTIONS on Information},
title={Rethinking the Rotation Invariance of Local Convolutional Features for Content-Based Image Retrieval},
year={2021},
volume={E104-D},
number={1},
pages={174-182},
abstract={Recently, local features computed using convolutional neural networks (CNNs) show good performance to image retrieval. The local convolutional features obtained by the CNNs (LC features) are designed to be translation invariant, however, they are inherently sensitive to rotation perturbations. This leads to miss-judgements in retrieval tasks. In this work, our objective is to enhance the robustness of LC features against image rotation. To do this, we conduct a thorough experimental evaluation of three candidate anti-rotation strategies (in-model data augmentation, in-model feature augmentation, and post-model feature augmentation), over two kinds of rotation attack (dataset attack and query attack). In the training procedure, we implement a data augmentation protocol and network augmentation method. In the test procedure, we develop a local transformed convolutional (LTC) feature extraction method, and evaluate it over different network configurations. We end up a series of good practices with steady quantitative supports, which lead to the best strategy for computing LC features with high rotation invariance in image retrieval.},
keywords={},
doi={10.1587/transinf.2020EDP7017},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - Rethinking the Rotation Invariance of Local Convolutional Features for Content-Based Image Retrieval
T2 - IEICE TRANSACTIONS on Information
SP - 174
EP - 182
AU - Longjiao ZHAO
AU - Yu WANG
AU - Jien KATO
PY - 2021
DO - 10.1587/transinf.2020EDP7017
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2021
AB - Recently, local features computed using convolutional neural networks (CNNs) show good performance to image retrieval. The local convolutional features obtained by the CNNs (LC features) are designed to be translation invariant, however, they are inherently sensitive to rotation perturbations. This leads to miss-judgements in retrieval tasks. In this work, our objective is to enhance the robustness of LC features against image rotation. To do this, we conduct a thorough experimental evaluation of three candidate anti-rotation strategies (in-model data augmentation, in-model feature augmentation, and post-model feature augmentation), over two kinds of rotation attack (dataset attack and query attack). In the training procedure, we implement a data augmentation protocol and network augmentation method. In the test procedure, we develop a local transformed convolutional (LTC) feature extraction method, and evaluate it over different network configurations. We end up a series of good practices with steady quantitative supports, which lead to the best strategy for computing LC features with high rotation invariance in image retrieval.
ER -