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
최근 CNN(Convolutional Neural Network)을 사용하여 계산된 로컬 특징은 이미지 검색에 좋은 성능을 보여줍니다. CNN에서 얻은 로컬 컨벌루션 기능(LC 기능)은 변환 불변으로 설계되었지만 본질적으로 회전 교란에 민감합니다. 이로 인해 검색 작업에서 잘못된 판단이 발생합니다. 이 작업에서 우리의 목표는 이미지 회전에 대한 LC 기능의 견고성을 향상시키는 것입니다. 이를 위해 두 가지 종류의 회전 공격(데이터 세트 공격 및 쿼리 공격)에 대해 세 가지 후보 회전 방지 전략(모델 내 데이터 증대, 모델 내 기능 증대 및 모델 후 기능 증대)에 대한 철저한 실험적 평가를 수행합니다. ). 훈련 절차에서는 데이터 증대 프로토콜과 네트워크 증대 방법을 구현합니다. 테스트 절차에서는 LTC(Local Transformed Convolutional) 특징 추출 방법을 개발하고 다양한 네트워크 구성에서 이를 평가합니다. 우리는 꾸준한 정량적 지원을 통해 일련의 모범 사례를 완성했으며, 이는 이미지 검색에서 회전 불변성이 높은 LC 기능을 계산하기 위한 최상의 전략으로 이어집니다.
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.
부
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
부
@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},}
부
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 -