Object Detection Based on Semantic Sampling and Localization Refinement

Yu Li; Shaoyan Gai; Feipeng Da; Ru Hong

doi:10.3788/LOP202259.1815015

Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1815015(2022)

Object Detection Based on Semantic Sampling and Localization Refinement

Yu Li^1,2, Shaoyan Gai^1,2,3, Feipeng Da^1,2,3、*, and Ru Hong^1,2

Author Affiliations

¹School of Automation, Southeast University, Nanjing 210096, Jiangsu, China

²Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education,Southeast University, Nanjing 210096, Jiangsu, China

³Shenzhen Research Institute, Southeast University, Shenzhen 518063, Guangdong, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Comparison of object detection architectures. (a) Architecture of RepPoints^[14]; (b) architecture of proposed detector

Download full size

Fig. 2. Overall architecture of proposed object detector. Dashed box: semantic based positioning module; dashed box: feature enhancement module

Download full size

Fig. 3. Architecture of localization subnet and classification subnet

Download full size

Fig. 4. Training samplers for object detection. (a) Center-based training sampler; (b) semantic-based training sampler

Download full size

Fig. 5. Qualitative results of proposed method on different datasets. (a), (b) VOC 2007; (c), (d) MS COCO

Download full size

Table 1. Experimental result comparison of proposed method to other methods on MS COCO test-dev

View table

Table 1. Experimental result comparison of proposed method to other methods on MS COCO test-dev

Method	Backbone	AP	$A P_{50}$	$A P_{75}$	$A P_{s}$	$A P_{m}$	$A P_{l}$	Time /ms
RetinaNet^［22］	ResNet-101	39.1	59.1	42.3	21.8	42.7	50.2	90
FCOS^［6］	ResNet-101	41.5	60.7	45.0	24.4	44.8	51.6	91
FSAF^［5］	ResNet-101	40.9	61.5	44.0	24.0	44.2	51.3	138
ATSS^［10］	ResNet-101	43.6	62.1	47.4	26.1	47.0	53.6	93
RepPoints^［14］	ResNet-101	41.0	62.9	44.3	23.6	44.1	51.7	87
CornerNet^［4］	Hourglass-104	40.5	56.5	43.1	19.4	42.7	53.9	227
ExtremeNet^［7］	Hourglass-104	40.2	55.5	43.2	20.4	43.2	53.1	348
CenterNet^［8］	Hourglass-104	42.1	61.1	45.9	24.1	45.5	52.8	298
LSNet^［21］	ResNeXt-101	43.9	63.1	47.8	26.6	47.1	55.4	138
Proposed	ResNet-101	42.8	65.1	46.3	26.1	47.3	55.8	78

Table 2. Experimental result comparison of integrating three modules into RepPoints

View table

Table 2. Experimental result comparison of integrating three modules into RepPoints

Method	AP	$A P_{50}$	$A P_{75}$	$A P_{s}$	$A P_{m}$	$A P_{l}$	Time /ms
Baseline RepPoints	39.1	60.5	42.1	21.2	41.2	50.0	85
RepPoints + LB	40.4	61.9	43.6	23.1	43.8	52.4	85
RepPoints + LB + FE	41.0	62.6	44.3	24.3	44.6	53.3	86
RepPoints + EO	39.2	61.7	42.2	21.4	42.8	50.6	76
Proposed（LB + FE+EO）	41.2	63.0	44.2	24.6	45.0	53.9	77

Table 3. Comparison of different transformation conversions
View table
Table 3. Comparison of different transformation conversions
Conversion function $N_{L}$ AP $A P_{50}$ $A P_{75}$ Time /ms
1×1 conv 40.4 60.2 43.6 85
Max-pooling 40.3 60.1 43.4 85
Max-pooling + avg-pooling 40.4 60.3 43.8 86

Table 4. Detection results with different location thresholds
View table
Table 4. Detection results with different location thresholds
$ϵ_{L}$ AP $A P_{50}$ $A P_{75}$
0.000 39.1 59.9 42.1
0.005 39.8 60.1 42.1
0.010 40.4 60.2 43.6
0.050 40.2 60.1 43.3
0.100 39.8 59.9 42.9

Table 5. Impact of applying efficient refinement optimization to different networks
View table
Table 5. Impact of applying efficient refinement optimization to different networks
Method EO FLOPs /G Param /M FPS /（frame·s^-1） Time /ms AP
RepPoints 190.16 36.62 11.8 85 39.1
✓ 190.06 35.97 13.1 76 39.2
Proposed 190.18 36.62 11.6 86 41.0
✓ 190.07 35.97 12.9 77 41.2

Tools

Get Citation

Copy Citation Text

Yu Li, Shaoyan Gai, Feipeng Da, Ru Hong. Object Detection Based on Semantic Sampling and Localization Refinement[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815015

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Machine Vision

Received: Jul. 23, 2021

Accepted: Aug. 31, 2021

Published Online: Sep. 5, 2022

The Author Email: Da Feipeng (qxxymm@163.com)

DOI:10.3788/LOP202259.1815015

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Experimental result comparison of proposed method to other methods on MS COCO test-dev

Table 1. Experimental result comparison of proposed method to other methods on MS COCO test-dev

Table 2. Experimental result comparison of integrating three modules into RepPoints

Table 2. Experimental result comparison of integrating three modules into RepPoints

Table 3. Comparison of different transformation conversions

Table 3. Comparison of different transformation conversions

Table 4. Detection results with different location thresholds

Table 4. Detection results with different location thresholds

Table 5. Impact of applying efficient refinement optimization to different networks

Table 5. Impact of applying efficient refinement optimization to different networks