Multi-Branch Person Re-Identification Based on Multi-Scale Attention

Cong Li; Min Jiang; Jun Kong

doi:10.3788/LOP57.201001

Laser & Optoelectronics Progress, Volume. 57, Issue 20, 201001(2020)

Multi-Branch Person Re-Identification Based on Multi-Scale Attention

Cong Li, Min Jiang^*, and Jun Kong

Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. Multi-branch person re-identification framework based on multi-scale attention mechanism

Download full size

Fig. 2. Structure of multi-scale attention module

Download full size

Fig. 3. Structure of multi-scale attention-aware feature DropBlock module

Download full size

Fig. 4. Comparison of two partition strategies

Download full size

Table 1. Effects of multi-scale attention module unit: %
View table
Table 1. Effects of multi-scale attention module unit: %
Method Market-1501 DukeMTMC-ReID
Rank-1 mAP Rank-1 mAP
Baseline 88.63 71.55 82.27 64.57
Baseline(with MSA) 90.15 73.03 84.47 67.02
Ours(without MSA) 94.42 86.65 89.74 79.18
Ours 95.37 88.02 90.57 80.92

Table 2. Effects of multi-scale attention-aware feature DropBlock module unit: %

View table

Table 2. Effects of multi-scale attention-aware feature DropBlock module unit: %

Method	Market-1501		DukeMTMC-ReID
Method	Rank-1	mAP	Rank-1	mAP
Baseline	88.63	71.55	82.27	64.57
Baseline(with BDB)	92.68	84.53	86.94	75.33
Baseline(with MSA-FD)	93.76	85.42	88.60	76.74
Ours(without MSA-FD)	94.94	86.72	89.59	79.61
Ours	95.37	88.02	90.57	80.92

Table 3. Effects of different partition strategies unit: %
View table
Table 3. Effects of different partition strategies unit: %
Partition strategy Market-1501
Rank-1 mAP
UP branch (H=8) 94.17 86.07
FP branch (H=9) 94.43 86.29
FP branch (H=10) 94.83 86.58
FP branch (H=11) 94.71 86.60
FP branch (H=12) 94.50 86.42

Table 4. Effect of joint multiple local feature strategy unit: %
View table
Table 4. Effect of joint multiple local feature strategy unit: %
Method Market-1501 DukeMTMC-ReID
Rank-1 mAP Rank-1 mAP
Baseline 88.63 71.55 82.27 64.57
Baseline+MSA-FD branch 93.76 85.42 88.60 76.74
Baseline+FP branch 94.83 86.58 89.50 79.47
All 95.37 88.02 90.57 80.92

Table 5. Comparison of results on Market-1501 unit: %

View table

Table 5. Comparison of results on Market-1501 unit: %

Partition strategy	Market-1501
Partition strategy	Rank-1	mAP
MSCAN^[23]	80.31	57.53
MGCAM^[22]	83.55	74.25
HA-CNN^[11]	91.20	75.70
AACN^[9]	85.90	66.87
SPReID^[25]	90.80	76.56
MLFN^[24]	90.00	74.30
PCB^[5]	93.80	81.60
MGN^[6]	95.70	86.90
Ours	95.37	88.02
Ours+Re-ranking	96.35	94.50

Table 6. Comparison of results on DukeMTMC-ReID unit: %

View table

Table 6. Comparison of results on DukeMTMC-ReID unit: %

Method	DukeMTMC-ReID
Method	Rank-1	mAP
JLML^[27]	73.30	56.40
SVDNet-ResNet50^[28]	76.70	56.80
AACN^[9]	76.84	59.25
SPReID^[25]	80.48	63.27
HACNN^[11]	80.50	63.80
MLFN^[24]	81.00	62.80
PCB^[5]	83.30	69.20
MGN^[6]	88.70	78.40
Ours	90.57	80.92
Ours+Re-ranking	93.00	90.74

Table 7. Comparison of results on CUHK03 unit: %

View table

Table 7. Comparison of results on CUHK03 unit: %

Method	CUHK03(Labeled)		CUHK03(Detected)
Method	Rank-1	mAP	Rank-1	mAP
DPFL^[29]	43.00	40.50	40.70	37.00
MGCAM^[22]	49.29	49.89	46.29	46.74
HA-CNN^[11]	44.40	41.00	41.70	38.60
MLFN^[24]	54.10	49.20	52.80	47.80
SVDNet-ResNet50^[28]	40.90	37.80	41.50	37.30
PCB^[5]	-	-	63.70	57.50
MGN^[6]	68.00	67.40	66.80	66.00
Ours	77.43	75.84	75.57	73.28
Ours+Re-ranking	85.30	87.15	83.64	85.17

Table 8. Comparison of computation speed on Market-1501
View table
Table 8. Comparison of computation speed on Market-1501
Method Computationtime perbatch /s Rank-1 /% mAP /%
Mobilenet_v2^[30] 0.138 87.0 68.5
HA-CNN^[11] 0.237 91.2 75.7
MLFN^[24] 0.585 90.0 74.3
PCB^[5] 0.331 93.8 81.6
MGN^[6] 0.561 95.7 86.9
Ours 0.544 95.37 88.02

Tools

Get Citation

Copy Citation Text

Cong Li, Min Jiang, Jun Kong. Multi-Branch Person Re-Identification Based on Multi-Scale Attention[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites