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 몇 년간 딥 네트워크 기반의 피쳐러닝은 개인 재식별(Re-ID)에 유용한 것으로 검증되었습니다. 그러나 대부분의 연구에서는 서로 다른 심층 기능의 융합을 고려하지 않고 단일 네트워크를 기준선으로 사용합니다. 서로 다른 네트워크의 주의 지도를 분석함으로써 우리는 서로 다른 네트워크에서 학습된 정보가 서로를 보완할 수 있음을 발견했습니다. 따라서 새로운 DNF(Dual Network Fusion) 프레임워크가 제안되었습니다. DNF는 트렁크 브랜치 03개와 보조 브랜치 1501개로 설계되었습니다. 트렁크 분기에서는 깊은 형상이 채널 방향을 따라 직접 계단식으로 배열됩니다. 보조 분기 중 하나는 채널 어텐션 분기로, 다양한 심층 기능에 가중치를 할당하는 데 사용됩니다. 또 다른 하나는 다중 손실 훈련 지점입니다. DNF의 성능을 검증하기 위해 CUHKXNUMXNP, Market-XNUMX 및 DukeMTMC-reID를 포함한 세 가지 벤치마크 데이터세트에서 테스트했습니다. 결과는 DNF를 사용하는 효과가 단일 네트워크보다 훨씬 우수하며 대부분의 최첨단 방법과 비교할 수 있음을 보여줍니다.
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.
부
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
부
@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},}
부
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 -