Integrating Coarse Granularity Part-Level Features with Supervised Global-Level Features for Person Re-Identification

doi:10.12142/ZTECOM.202101009

摘要/Abstract

Abstract:

Person re-identification (Re-ID) has achieved great progress in recent years. However, person Re-ID methods are still suffering from body part missing and occlusion problems, which makes the learned representations less reliable. In this paper, we propose a robust coarse granularity part-level network (CGPN) for person Re-ID, which extracts robust regional features and integrates supervised global features for pedestrian images. CGPN gains two-fold benefit toward higher accuracy for person Re-ID. On one hand, CGPN learns to extract effective regional features for pedestrian images. On the other hand, compared with extracting global features directly by backbone network, CGPN learns to extract more accurate global features with a supervision strategy. The single model trained on three Re-ID datasets achieves state-of-the-art performances. Especially on CUHK03, the most challenging Re-ID dataset, we obtain a top result of Rank-1/mean average precision (mAP)=87.1%/83.6% without re-ranking.

Key words: person Re-ID, supervision, coarse granularity

. [J]. ZTE Communications, 2021, 19(1): 72-81.

CAO Jiahao, MAO Xiaofei, LI Dongfang, ZHENG Qingfang, JIA Xia. Integrating Coarse Granularity Part-Level Features with Supervised Global-Level Features for Person Re-Identification[J]. ZTE Communications, 2021, 19(1): 72-81.

图/表 10

参考文献 39

1	CHANG X B, HOSPEDALES T M, XIANG T. Multi⁃level factorisation net for person re⁃identification [EB/OL]. (2018⁃04⁃17) [2020⁃12⁃05].
2	LIU H, FENG J, QI M, et al. End⁃to⁃end comparative attention networks for person re⁃identification [J]. IEEE transactions on image processing, 2017, 26(7): 3492–3506. DOI: 10.1109/tip.2017.2700762 DOI
3	SARFRAZ M S, SCHUMANN A, EBERLE A, et al. A pose⁃sensitive embedding for person re⁃identification with expanded cross neighborhood re⁃ranking [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 420–429. DOI: 10.1109/cvpr.2018.00051 DOI
4	SHEN Y T, LI H S, XIAO T, et al. Deep group⁃shuffling random walk for person re⁃identification [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 2265–2274. DOI:10.1109/CVPR.2018.00241 DOI
5	WANG G S, YUAN Y F, CHEN X, et al. Learning discriminative features with multiple granularities for person re⁃identification [C]//Proceedings of the 26th ACM International Conference On Multimedia. Seoul, Korea: ACM, 2018: 274–282. DOI: 10.1145/3240508.3240552 DOI
6	SUN Y F, ZHENG L, YANG Y, et al. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline) [C]//Proceedings of the European Conference on Computer Vision. Munich, German: ECCV, 2018: 480–496. DOI: 10.1007/978-3-030-01225-0_30 DOI
7	ZHENG F, DENG C, SUN X, et al. Pyramidal person re⁃identification via multi⁃loss dynamic training [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, USA: CVPR, 2019: 8514–8522. DOI: 10.1109/cvpr.2019.00871 DOI
8	SHEN Y, LIN W, YAN J, et al. Person re⁃identification with correspondence structure learning [C]//Proceedings of the IEEE international conference on computer vision. Santiago, Chile: IEEE, 2015: 3200–3208. DOI: 10.1109/iccv.2015.366 DOI
9	VARIOR R R, SHUAI B, LU J W, et al. A siamese long short⁃term memory architecture for human re⁃identification [C]//European Conference on Computer Vision. Amsterdam, Netherlands, ECCV, 2016: 135–153. DOI: 10.1007/978-3-319-46478-7_9 DOI
10	ZHENG L, HUANG Y J, LU H C, et al. Pose⁃invariant embedding for deep person re⁃identification [J]. IEEE transactions on image processing, 2019, 28(9): 4500–4509. DOI: 10.1109/tip.2019.2910414 DOI
11	LI W, ZHAO R, XIAO T, et al. DeepReID: deep filter pairing neural network for person re⁃identification [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 152–159. DOI:10.1109/CVPR.2014.27 DOI
12	YI D, LEI Z, LIAO S C, et al. Deep metric learning for person re⁃identification [C]//2014 22nd International Conference on Pattern Recognition. Stockholm, Sweden: IEEE, 2014: 34–39. DOI: 10.1109/icpr.2014.16 DOI
13	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: CVPR, 2016: 770–778. DOI: 10.1109/cvpr.2016.90 DOI
14	LI W, ZHU X T, GONG S G. Harmonious attention network for person re⁃identification [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: CVPR, 2018: 2285–2294. DOI: 10.1109/cvpr.2018.00243 DOI
15	LI D W, CHEN X T, ZHANG Z, et al. Learning deep context⁃aware features over body and latent parts for person re⁃identification [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: CVPR, 2017: 7398–7407. DOI: 10.1109/CVPR.2017.782 DOI
16	ZHAO L M, LI X, ZHUANG Y T, et al. Deeply⁃learned part⁃aligned representations for person re⁃identification [C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice， Italy: IEEE, 2017: 3219–3228. DOI:10.1109/iccv.2017.349 DOI
17	JADERBERG M, SIMONYAN K, ZISSERMAN A. Spatial transformer networks [C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada, 2015: 2017–2025
18	LI S, BAK S, CARR P, et al. Diversity regularized spatiotemporal attention for video⁃based person re⁃identification [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 369–378. DOI: 10.1109/CVPR.2018.00046 DOI
19	XU J, ZHAO R, ZHU F, et al. Attention⁃aware compositional network for person re⁃identification [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: CVPR, 2018: 2119–2128. DOI: 10.1109/cvpr.2018.00226 DOI
20	SARFRAZ M S, SCHUMANN A, EBERLE A, et al. A pose⁃sensitive embedding for person re⁃identification with expanded cross neighborhood re⁃ranking [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: CVPR, 2018: 420–429. DOI: 10.1109/CVPR.2018.00051 DOI
21	HUANG H J, YANG W J, CHEN X T, et al. EANet: enhancing alignment for cross⁃domain person re⁃identification [EB/OL]. (2018⁃12⁃19) [2020⁃12⁃05].
22	MIAO J X, WU Y, LIU P, et al. Pose⁃guided feature alignment for occluded person re⁃identification [C]//2019 IEEE International Conference on Computer Vision. Seoul, South Korea: IEEE, 2019: 542–551. DOI:10.1109/ICCV.2019.00063 DOI
23	HERMANS A, BEYER L, LEIBE B. In defense of the triplet loss for person re⁃identification [EB/OL]. (2017⁃03⁃22)[2020⁃12⁃12].
24	ZHENG L, SHEN L Y, TIAN L, et al. Scalable person re⁃identification: A benchmark [C]//2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 1116–1124. DOI: 10.1109/ICCV.2015.133 DOI
25	RISTANI E, SOLERA F, ZOU R, et al. Performance measures and a data set for multi⁃target, multi⁃camera tracking [C]//European Conference on Computer Vision. Amsterdam, Netherlands: ECCV, 2016: 17–35. DOI: 10.1007/978-3-319-48881-3_2 DOI
26	LI W, ZHAO R, XIAO T, et al. DeepReID: deep filter pairing neural network for person re⁃identification [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 152–159. DOI:10.1109/CVPR.2014.27 DOI
27	FELZENSZWALB P, MCALLESTER D, RAMANAN D. discriminatively trainedA, multiscale, deformable part model [C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2008: 1–8. DOI: 10.1109/CVPR.2008.4587597
	`
28	ZHONG Z, ZHENG L, CAO D L, et al. Re⁃ranking person re⁃identification with k⁃reciprocal encoding [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 3652–3661. DOI:10.1109/CVPR.2017.389 DOI
29	ZHENG L, YANG Y, HAUPTMANN A G. Person re⁃identification: past, present and future [EB/OL]. [2020⁃12⁃05].
30	ZHENG Z D, ZHENG L, YANG Y. Pedestrian alignment network for large⁃scale person re⁃identification [J]. IEEE transactions on circuits and systems for video technology, 2019, 29(10): 3037–3045. DOI:10.1109/TCSVT.2018.2873599 DOI
31	SUN Y F, ZHENG L, DENG W J, et al. SVDNet for pedestrian retrieval [C]//2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 3820–3828. DOI: 10.1109/ICCV.2017.410 DOI
32	WANG Z, HU R M, CHEN C, et al. Person re⁃identification via discrepancy matrix and matrix metric [J]. IEEE transactions on cybernetics, 2018, 48(10): 3006⁃3020. DOI: 10.1109/TCYB.2017.2755044 DOI
33	SONG C F, HUANG Y, OUYANG W L, et al. Mask⁃guided contrastive attention model for person re⁃identification [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 1179–1188. DOI: 10.1109/CVPR.2018.00129 DOI
34	WANG Z, JIANG J J, WU Y, et al. Learning sparse and identity⁃preserved hidden attributes for person re⁃identification [J]. IEEE transactions on image processing, 2019, 29: 2013⁃2025. DOI: 10.1109/TIP.2019.2946975 DOI
35	SUN Y F, XU Q, LI Y L, et al. Perceive where to focus: Learning visibility⁃aware part⁃level features for partial person re⁃identification [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 393–402. DOI: 10.1109/CVPR.2019.00048 DOI
36	FAN X, LUO H, ZHANG X, et al. SCPNet: spatial⁃channel parallelism network for joint holistic and partial person re⁃identification [C]//Asian Conference on Computer Vision. Perth, Australia: ACCV, 2018: 19–34. DOI: 10.1007/978-3-030-20890-5_2 DOI
37	FAN X, JIANG W, LUO H, et al. SphereReID: Deep hypersphere manifold embedding for person re⁃identification [J]. Journal of visual communication and image representation, 2019, 60: 51–58. DOI: 10.1016/j.jvcir.2019.01.010 DOI
38	ZHANG Z Z, LAN C L, ZENG W J, et al. Densely semantically aligned person re⁃identification [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 667–676. DOI:10.1109/CVPR.2019.00076 DOI
39	JIN X, LAN C L, ZENG W J, et al. Semantics⁃aligned representation learning for person re⁃identification [EB/OL]. (2019⁃05⁃30) [2020⁃12⁃05].

Method	Market-1501		DukeMTMC-reID		CUHK03
Method	Rank-1/%	mAP/%	Rank-1/%	mAP/%	Rank-1/%	mAP/%
IDE^[29]	-	-	-	-	22.2	21.0
PAN^[30]	-	-	-	-	36.9	35.0
SVDNet^[31]	-	-	-	-	40.9	37.8
IDE(R)+DM^3[32]	73.4	51.8	-	-	-	-
MGCAM^[33]	83.8	74.3	-	-	50.1	50.2
DHA-Net + ISO(Aggr)^[34]	88.2	70.1	74.2	54.5	-	-
HA-CNN^[14]	91.2	75.7	80.5	63.8	44.4	41.0
VPM^[35]	93.0	80.8	83.6	72.6	-	-
SCP^[36]	94.1	-	84.8	-	-	-
PCB+RPP^[6]	93.8	81.6	83.3	69.2	-	-
SphereReID^[37]	94.4	83.6	83.9	68.5	-	-
MGN^[5]	95.7	86.9	88.7	78.4	68.0	67.4
DSA^[38]	95.7	87.6	86.2	74.3	78.9	75.2
Pyramid^[7]	95.7	88.2	89.0	79.0	78.9	76.9
SAN^[39]	96.1	88.0	87.9	75.5	80.1	76.4
CGPN	96.1	89.9	90.4	80.9	87.1	83.6

Method	Market-1501		DukeMTMC-reID		CUHK03
Method	Rank-1/%	mAP/%	Rank-1/%	mAP/%	Rank-1/%	mAP/%
IDE^[29]	-	-	-	-	22.2	21.0
PAN^[30]	-	-	-	-	36.9	35.0
SVDNet^[31]	-	-	-	-	40.9	37.8
IDE(R)+DM^3[32]	73.4	51.8	-	-	-	-
MGCAM^[33]	83.8	74.3	-	-	50.1	50.2
DHA-Net + ISO(Aggr)^[34]	88.2	70.1	74.2	54.5	-	-
HA-CNN^[14]	91.2	75.7	80.5	63.8	44.4	41.0
VPM^[35]	93.0	80.8	83.6	72.6	-	-
SCP^[36]	94.1	-	84.8	-	-	-
PCB+RPP^[6]	93.8	81.6	83.3	69.2	-	-
SphereReID^[37]	94.4	83.6	83.9	68.5	-	-
MGN^[5]	95.7	86.9	88.7	78.4	68.0	67.4
DSA^[38]	95.7	87.6	86.2	74.3	78.9	75.2
Pyramid^[7]	95.7	88.2	89.0	79.0	78.9	76.9
SAN^[39]	96.1	88.0	87.9	75.5	80.1	76.4
CGPN	96.1	89.9	90.4	80.9	87.1	83.6

Method	Occluded-DukeMTMC
Method	Rank-1/%	Rank-5/%	Rank-10/%	mAP/%
HA-CNN^[14]	34.4	51.9	59.4	26.0
PCB+RPP^[6]	42.6	57.1	62.9	33.7
PGFA^[22]	51.4	68.6	74.9	37.3
CGPN	58.5	73.4	78.4	50.9

Method	Occluded-DukeMTMC
Method	Rank-1/%	Rank-5/%	Rank-10/%	mAP/%
HA-CNN^[14]	34.4	51.9	59.4	26.0
PCB+RPP^[6]	42.6	57.1	62.9	33.7
PGFA^[22]	51.4	68.6	74.9	37.3
CGPN	58.5	73.4	78.4	50.9

Method	Market-1501		DuckMTMC-reID		CUHK03
Method	Rank-1/%	mAP/%	Rank-1/%	mAP/%	Rank-1/%	mAP/%
CGPN-1	94.9	87.9	89.3	78.4	82.4	79.9
CGPN-2	95.3	89.4	90.3	80.2	85.3	82.5
CGPN-3	94.2	86.2	88.6	76.9	84.3	81.0
CGPN-4	95.2	89.3	90.0	79.9	83.4	80.7
CGPN	96.1	89.9	90.4	80.9	87.1	83.6