

浏览全部资源
扫码关注微信
江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122
Received:03 September 2020,
Revised:2021-01-22,
Published:25 August 2021
移动端阅览
匡澄,陈莹.基于多粒度特征融合网络的行人重识别[J].电子学报,2021,49(08):1541-1550.
KUANG Cheng,CHEN Ying.Multi-granularity Feature Fusion Network for Person Re-Identification[J].ACTA ELECTRONICA SINICA,2021,49(08):1541-1550.
匡澄,陈莹.基于多粒度特征融合网络的行人重识别[J].电子学报,2021,49(08):1541-1550. DOI: 10.12263/DZXB.20200974.
KUANG Cheng,CHEN Ying.Multi-granularity Feature Fusion Network for Person Re-Identification[J].ACTA ELECTRONICA SINICA,2021,49(08):1541-1550. DOI: 10.12263/DZXB.20200974.
行人重识别旨在跨监控设备下检索出特定的行人目标. 为捕捉行人图像的多粒度特征进而提高识别精度,基于OSNet基准网络提出一种多粒度特征融合网络(Multi-granularity Feature Fusion Network for Person Re-Identi-fication
MFN)进行端对端的学习. MFN由全局分支、特征擦除分支和局部分支组成,其中特征擦除分支由双通道注意力擦除模型构成,此模型包含通道注意力擦除模块(Channel Attention-based Dropout Moudle
CDM)和空间注意力擦除模块(Spatial Attention-based Dropout Moudle
SDM). CDM对通道的注意力强度排序并擦除低注意力通道,SDM在空间维度上以一定概率擦除最具有判别力的特征,两者通过并联方式相互作用,提高模型的识别能力. 全局分支采用特征金字塔结构提取多尺度特征,局部分支将特征均匀切块后级联成一个单一特征,提取关键局部信息. 大量实验结果表明了本文方法的有效性,在Market1501、DukeMTMC-reID和CUHK03-Labeled(Detected)数据集上,mAP/Rank-1分别达到了90.1%/95.8%、81.8%/91.4%和80.7%/82.3%(78.7%/81.6%),大幅优于其他现有方法.
For the purpose of capturing the multi-granularity features and improving the recognition accuracy
a multi-granularity feature fusion network for person re-identification (MFN) is proposed based on the omist-scale network (OSNet). The MFN network is composed of a global branch
a feature dropout branch and a local branch. The feature dropout branch consists of a dual-channel attention dropout model
which includes a channel attention-based dropout moudle (CDM) and a Spatial attention-based dropout moudle (SDM). CDM sorts the attention intensity and dropouts low attention channels
and SDM dropouts the most discriminative features with a certain probability in the spatial dimension. The global branch uses the feature pyramid structure to extract multi-scale features
and the local branch employs a uniform partition strategy to produce local features which are cascaded into a single one for key local information extraction. Experiments on the large scale datasets show the effectiveness of MFN. On the Market1501
DukeMTMC-reID and CUHK03 -Labeled (Detected) datasets
mAP/Rank-1 of MFN reaches 90.1%/95.8%
81.8%/91.4% and 80.7%/82.3% (78.7%/81.6%)
which is superior to other existing methods.
罗浩 , 姜伟 , 范星 , 等 . 基于深度学习的行人重识别研究进展 [J]. 自动化学报 , 2019 , 45 ( 11 ): 2032 - 2049 .
Luo H , Jiang W , Fan X , et al . A survey on deep learning based Person Re-Identification [J]. Acta Automatica Sinica , 2019 , 45 ( 11 ): 2032 - 2049 . (in Chinese)
Weinberger K Q , Saul L K . Fast solvers and efficient implementations for distance metric learning [A]. Proceedings of the 25th International Conference on Machine Learning [C]. Helsinki, Finland : ICML , 2008 . 1160 - 1167 .
Liao S , Hu Y , Zhu X , et al . Person re-identification by local maximal occurrence representation and metric learning [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Boston, MA, USA : CVPR , 2015 . 2197 - 2206 .
Sun Y , Zheng L , Yang Y , et al . Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline) [A]. Proceedings of the European Conference on Computer Vision [C]. Munich, Germany : ECCV , 2018 . 480 - 496 .
Wang G , Yuan Y , Chen X , et al . Learning discriminative features with multiple granularities for person re-identification [A]. Proceedings of the 26th ACM International Conference on Multimedia [C]. Seoul, Korea : ACM , 2018 . 274 - 282 .
陈巧媛 , 陈莹 . 通道互注意机制下的部位对齐行人再识别 [J]. 计算机辅助设计与图形学学报 , 2020 , 32 ( 8 ): 1258 - 1266 .
Chen Q Y , Chen Y . Correlation channel-wise based part aligned representations for person re-identification [J]. Journal of Computer-Aided Design & Computer Graphics , 2020 , 32 ( 8 ): 1258 - 1266 . (in Chinese)
Zheng F , Deng C , Sun X , et al . Pyramidal person re-identification via multi-loss dynamic training [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Long Beach, CA, USA : CVPR , 2019 . 8514 - 8522 .
DeVries T , Taylor G W . Improved regularization of convolutional neural networks with cutout [EB/OL]. https://arxiv. org/abs/1708. 04552 https://arxiv.org/abs/1708.04552 , 2017-08-15 .
Zhong Z , Zheng L , Kang G , et al . Random erasing data augmentation [A]. Association for the Advance of Artificial Intelligence [C]. New York, USA : AAAI , 2020 . 13001 - 13008 .
Ghiasi G , Lin T Y , Le Q V . Dropblock: A regularization method for convolutional networks [A]. Neural Information Processing Systems [C]. Montreal, Canada : NIPS , 2018 . 10727 - 10737 .
Tompson J , Goroshin R , Jain A , et al . Efficient object localization using convolutional networks [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Boston, MA, USA : CVPR , 2015 . 648 - 656 .
Dai Z , Chen M , Gu X , et al . Batch DropBlock network for person re-identification and beyond [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Long Beach, CA, USA : CVPR , 2019 . 3691 - 3701 .
Zhou K , Yang Y , Cavallaro A , et al . Omni-scale feature learning for person re-identification [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Seoul, Korea : ICCV , 2019 . 3702 - 3712 .
Zheng L , Shen L , Tian L , et al . Scalable person re-identification: A benchmark [A]. Proceedings of The IEEE International Conference on Computer Vision [C]. Santiago, Chile : ICCV , 2015 . 1116 - 1124 .
Ristani E , Solera F , Zou R , et al . Performance measures and a data set for multi-target , multi-camera tracking[A]. European Conference on Computer Vision [C]. Amsterdam, Netherlands : ECCV , 2016 . 17 - 35 .
Li W , Zhao R , Xiao T , et al . Deepreid: Deep filter pairing neural network for person re-identification [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Columbus, USA : CVPR , 2014 . 152 - 159 .
Chen T , Ding S , Xie J , et al . Abd-net: Attentive but diverse person re-identification [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Seoul, Korea : ICCV , 2019 . 8351 - 8361 .
Lin T Y , Dollár P , Girshick R , et al . Feature pyramid networks for object detection [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Honolulu, HI, USA : CVPR , 2017 . 2117 - 2125 .
Lin T Y , Maire M , Belongie S , et al . Microsoft coco: Common objects in context [A]. European Conference on Computer Vision [C]. Zurich, Switzerland : ECCV , 2014 . 740 - 755 .
Choe J , Shim H . Attention-based dropout layer for weakly supervised object localization [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Long Beach, CA, USA : CVPR , 2019 . 2219 - 2228 .
Xie B , Wu X , Zhang S , et al . Learning diverse features with part-level resolution for person re-identification [EB/OL]. https: //arxiv.org/abs/2001.07442 https://arxiv.org/abs/2001.07442 , 2020-01-21 .
Wen Y , Zhang K , Li Z , et al . A discriminative feature learning approach for deep face recognition [A]. European Conference on Computer Vision [C]. Amsterdam, Netherlands : ECCV , 2016 . 499 - 515 .
Hermans A , Beyer L , Leibe B . In defense of the triplet loss for person re-identification [EB/OL]. https: / /arxiv . org/ abs/ 1703 . 07737 , 2017-03-22 .
Szegedy C , Vanhoucke V , Ioffe S , et al . Rethinking the inception architecture for computer vision [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Las Vegas, NV, USA : CVPR , 2016 . 2818 - 2826 .
Zhou K , Xiang T . Torchreid: A library for deep learning person re-identification in pytorch [EB/OL]. https: //arxiv. org/abs/1910.10093 https://arxiv.org/abs/1910.10093 , 2019-10-22 .
Zhong Z , Zheng L , Cao D , et al . Re-ranking person re-identification with k-reciprocal encoding [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Honolulu, HI, USA : CVPR , 2017 . 1318 - 1327 .
Li W , Zhu X , Gong S . Harmonious attention network for person re-identification [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Salt Lake City, UT, USA : CVPR , 2018 . 2285 - 2294 .
Chen B , Deng W , Hu J . Mixed high-order attention network for person re-identification [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Seoul, Korea : ICCV , 2019 . 371 - 381 .
Xia B N , Gong Y , Zhang Y , et al . Second-order non-local attention networks for person re-identification [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Long Beach, CA, USA : CVPR , 2019 . 3760 - 3769 .
Quan R , Dong X , Wu Y , et al . Auto-reid: Searching for a part-aware convnet for person re-identification [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Long Beach, CA, USA : CVPR , 2019 . 3750 - 3759 .
Wang G , Yang S , Liu H , et al . High-order information matters: Learning relation and topology for occluded person re-identification [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Seattle, WA, USA : CVPR , 2020 . 6449 - 6458 .
Jin X , Lan C , Zeng W , et al . Style normalization and restitution for generalizable person re-identification [A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C]. Seattle, WA, USA : CVPR , 2020 . 3143 - 3152 .
Selvaraju R R , Cogswell M , Das A , et al . Visual explanations from deep networks via gradient-based localization [A]. Proceedings of the IEEE International Conference on Computer Vision [C]. Venice, Italy : ICCV , 2017 . 618 - 626 .
0
Views
14
下载量
8
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621