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
Pembelajaran ciri berdasarkan rangkaian dalam telah disahkan sebagai bermanfaat untuk pengenalan semula orang (Re-ID) dalam beberapa tahun kebelakangan ini. Walau bagaimanapun, kebanyakan penyelidikan menggunakan satu rangkaian sebagai garis dasar, tanpa mengambil kira gabungan ciri dalam yang berbeza. Dengan menganalisis peta perhatian rangkaian yang berbeza, kami mendapati bahawa maklumat yang dipelajari oleh rangkaian yang berbeza boleh saling melengkapi. Oleh itu, rangka kerja Gabungan Rangkaian Ganda (DNF) baru dicadangkan. DNF direka bentuk dengan cawangan batang dan dua cawangan tambahan. Dalam dahan batang, ciri-ciri dalam dilantunkan terus di sepanjang arah saluran. Salah satu cabang tambahan ialah cawangan perhatian saluran, yang digunakan untuk memperuntukkan berat untuk ciri dalam yang berbeza. Satu lagi adalah cawangan latihan multi-rugi. Untuk mengesahkan prestasi DNF, kami mengujinya pada tiga set data penanda aras, termasuk CUHK03NP, Market-1501 dan DukeMTMC-reID. Keputusan menunjukkan bahawa kesan penggunaan DNF adalah jauh lebih baik daripada rangkaian tunggal dan setanding dengan kebanyakan kaedah terkini.
Lin DU
Army Engineering University of PLA
Chang TIAN
Army Engineering University of PLA
Mingyong ZENG
the Jiangnan Institute of Computing Technology
Jiabao WANG
Army Engineering University of PLA
Shanshan JIAO
Army Engineering University of PLA
Qing SHEN
Army Engineering University of PLA
Guodong WU
Army Engineering University of PLA
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.
Salinan
Lin DU, Chang TIAN, Mingyong ZENG, Jiabao WANG, Shanshan JIAO, Qing SHEN, Guodong WU, "Dual Network Fusion for Person Re-Identification" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 3, pp. 643-648, March 2020, doi: 10.1587/transfun.2019EAL2116.
Abstract: Feature learning based on deep network has been verified as beneficial for person re-identification (Re-ID) in recent years. However, most researches use a single network as the baseline, without considering the fusion of different deep features. By analyzing the attention maps of different networks, we find that the information learned by different networks can complement each other. Therefore, a novel Dual Network Fusion (DNF) framework is proposed. DNF is designed with a trunk branch and two auxiliary branches. In the trunk branch, deep features are cascaded directly along the channel direction. One of the auxiliary branch is channel attention branch, which is used to allocate weight for different deep features. Another one is multi-loss training branch. To verify the performance of DNF, we test it on three benchmark datasets, including CUHK03NP, Market-1501 and DukeMTMC-reID. The results show that the effect of using DNF is significantly better than a single network and is comparable to most state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019EAL2116/_p
Salinan
@ARTICLE{e103-a_3_643,
author={Lin DU, Chang TIAN, Mingyong ZENG, Jiabao WANG, Shanshan JIAO, Qing SHEN, Guodong WU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Dual Network Fusion for Person Re-Identification},
year={2020},
volume={E103-A},
number={3},
pages={643-648},
abstract={Feature learning based on deep network has been verified as beneficial for person re-identification (Re-ID) in recent years. However, most researches use a single network as the baseline, without considering the fusion of different deep features. By analyzing the attention maps of different networks, we find that the information learned by different networks can complement each other. Therefore, a novel Dual Network Fusion (DNF) framework is proposed. DNF is designed with a trunk branch and two auxiliary branches. In the trunk branch, deep features are cascaded directly along the channel direction. One of the auxiliary branch is channel attention branch, which is used to allocate weight for different deep features. Another one is multi-loss training branch. To verify the performance of DNF, we test it on three benchmark datasets, including CUHK03NP, Market-1501 and DukeMTMC-reID. The results show that the effect of using DNF is significantly better than a single network and is comparable to most state-of-the-art methods.},
keywords={},
doi={10.1587/transfun.2019EAL2116},
ISSN={1745-1337},
month={March},}
Salinan
TY - JOUR
TI - Dual Network Fusion for Person Re-Identification
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 643
EP - 648
AU - Lin DU
AU - Chang TIAN
AU - Mingyong ZENG
AU - Jiabao WANG
AU - Shanshan JIAO
AU - Qing SHEN
AU - Guodong WU
PY - 2020
DO - 10.1587/transfun.2019EAL2116
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2020
AB - Feature learning based on deep network has been verified as beneficial for person re-identification (Re-ID) in recent years. However, most researches use a single network as the baseline, without considering the fusion of different deep features. By analyzing the attention maps of different networks, we find that the information learned by different networks can complement each other. Therefore, a novel Dual Network Fusion (DNF) framework is proposed. DNF is designed with a trunk branch and two auxiliary branches. In the trunk branch, deep features are cascaded directly along the channel direction. One of the auxiliary branch is channel attention branch, which is used to allocate weight for different deep features. Another one is multi-loss training branch. To verify the performance of DNF, we test it on three benchmark datasets, including CUHK03NP, Market-1501 and DukeMTMC-reID. The results show that the effect of using DNF is significantly better than a single network and is comparable to most state-of-the-art methods.
ER -