Few-shot prohibited item segmentation algorithm based on graph matching network

Zhenyue Zhu; Shujing Lv; Yue Lv

doi:10.3788/IRLA20210075

Journals >Infrared and Laser Engineering >Volume 50 >Issue 11 >Page 20210075 > Article

Infrared and Laser Engineering
Vol. 50, Issue 11, 20210075 (2021)

Few-shot prohibited item segmentation algorithm based on graph matching network

Zhenyue Zhu¹, Shujing Lv^1、2、*, and Yue Lv^1、2

Author Affiliations

¹Department of Computer Science and Technology, East China Normal University, Shanghai 200062, China

²Shanghai Key Laboratory of Multidimensional Information Processing, Shanghai 200241, China

show less

DOI: 10.3788/IRLA20210075 Cite this Article

Zhenyue Zhu, Shujing Lv, Yue Lv. Few-shot prohibited item segmentation algorithm based on graph matching network[J]. Infrared and Laser Engineering, 2021, 50(11): 20210075 Copy Citation Text

show less

Fig. 1. Overview of proposed framework in the 1-shot prohibited item segmentation

Download full size | View in the Article

Fig. 2. Structure diagram of the node attention module

Download full size | View in the Article

Fig. 3. Experimental effect results on SIXray dataset. (a) Support image; (b) Support image mask; (c) Query image; (d) Segmentation result, of which red region is the predicted prohibited item region

Download full size | View in the Article

Fig. 4. Experimental effect results on Xray-PI dataset. (a) Support image; (b) Support image mask; (c) Query image; (d) Segmentation result, of which red region is the predicted prohibited item region

Download full size | View in the Article

Operational layer		Configuration
Graph embedding	Input image	321×321×3
	Convolution layer	#maps: 64，k: 7×7，s: 2×2
	Maxpool layer	w: 3×3，s: 2×2
	Convolution layer	$\left[ \begin{array}{l}{\rm{\# maps:} }\;\;{\rm{64,} }\;{{k:} }\;{\rm{1 \times 1} }\;{{s:} }\;{\rm{1 \times 1} }\\{\rm{\# maps:} }\;\;{\rm{64,} }\;{{k:} }\;{\rm{3 \times 3} }\;{{s:} }\;{\rm{1 \times 1} }\\{\rm{\# maps:} }\;{\rm{256,} }\;{{k:} }\;{\rm{1 \times 1} }\;{{s:} }\;{\rm{1 \times 1} }\end{array} \right]{\rm{ \times 3} }$
	Convolution layer	$\left[ \begin{array}{l}{\rm{\# maps:} }\;\;128{\rm{,} }\;{{k:} }\;{\rm{1 \times 1} }\;{{s:} }\;2{\rm{ \times 2} }\\{\rm{\# maps:} }\;\;128{\rm{,} }\;{{k:} }\;{\rm{3 \times 3} }\;{{s:} }\;2{\rm{ \times 2} }\\{\rm{\# maps:} }\;\;512{\rm{,} }\;{{k:} }\;{\rm{1 \times 1} }\;{{s:} }\;2{\rm{ \times 2} }\end{array} \right]{\rm{ \times 4} }$
	Convolution layer	$\left[ \begin{array}{l}{\rm{\# maps:} }\;\;\;256{\rm{,} }\;{ {k:} }\;{\rm{1 \times 1} }\;{ {s:} }\;1{\rm{ \times 1} }\\{\rm{\# maps:} }\;\;\;256{\rm{,} }\;{ {k:} }\;{\rm{3 \times 3} }\;{ {s:} }\;1{\rm{ \times 1} }\\{\rm{\# maps:} }\;\;1024{\rm{,} }\;{ {k:} }\;{\rm{1 \times 1} }\;{ {s:} }\;1{\rm{ \times 1} }\end{array} \right]{\rm{ \times 6} }$
	Convolution layer	#maps: 256，k: 1×1，s: 1×1
Graph matching	Convolution layer	#maps: 256，k: 1×1，s: 1×1
	Avgpool layer	w: 11×11，s: 1×1
	Convolution layer	#maps: 256，k: 1×1，s: 1×1
	Convolution layer	#maps: 256，k: 1×1，s: 1×1
	Maxpool layer	w: 10×10，s: 1×1
Segmentation	Convolution layer	#maps: 256，k: 1×1，s: 1×1
	Convolution layer	$\left[ \begin{array}{l}{\rm{\# maps:} }\;\;\;256{\rm{,} }\;{{k:} }\;3{\rm{ \times 3} }\;{{s:} }\;1{\rm{ \times 1} }\\{\rm{\# maps:} }\;\;\;256{\rm{,} }\;{{k:} }\;{\rm{3 \times 3} }\;{{s:} }\;1{\rm{ \times 1} }\end{array} \right]{\rm{ \times 3} }$
	Convolution layer	#maps: 1，k: 1×1，s: 1×1

Table 1. Parameter setting of prohibited item segmentation model based on graph matching network

View in the Article

Filter	Size	meanIoU
Filter	Size	Xray-PI	SIXray
Average filter	5	48.8%	34.0%
	10	50.4%	35.8%
	15	49.7%	35.5%
Maximum filter	5	50.1%	34.8%
	10	51.2%	36.4%
	15	50.4%	35.3%

Table 2. Segmentation performance of model with different filters and length of subgraphs

View in the Article

Methods		Gun	Knife	Wrench	Pliers	Scissors	meanIoU
1-shot	CANet^[13]	40.3	41.6	35.2	33.9	18.3	33.9%
	PGNet^[16]	38.9	41.5	37.4	33.2	18.0	33.8%
	Ours	41.4	42.1	35.6	34.0	28.5	36.4%
5-shot	CANet^[13]	43.0	43.2	36.8	35.4	18.9	35.5%
	PGNet^[16]	41.1	42.9	37.0	35.7	19.1	35.2%
	Ours	43.7	43.4	36.3	35.9	29.3	37.7%

Table 3. Segmentation performance of 1-shot task and 5-shot task on SIXray dataset

View in the Article

Methods		Firework	Firecracker	Bottle	Gun	Wrench	Pliers	Blade	meanIoU
1-shot	CANet^[13]	51.4	45.5	42.2	48.1	34.7	53.0	67.9	48.9%
	PGNet^[16]	44.1	41.9	31.8	47.1	36.3	51.1	66.4	45.5%
	Proposed	52.9	45.7	47.4	51.2	37.5	55.5	68.7	51.2%
5-shot	CANet^[13]	54.8	47.6	45.2	49.5	35.6	56.1	68.0	51.0%
	PGNet^[16]	46.0	43.0	35.1	48.5	37.1	55.6	68.3	47.7%
	Proposed	55.4	49.1	48.7	53.6	38.5	56.4	68.9	52.9%

Table 4. Segmentation performance of 1-shot task and 5-shot task on Xray-PI dataset

Zhenyue Zhu, Shujing Lv, Yue Lv. Few-shot prohibited item segmentation algorithm based on graph matching network[J]. Infrared and Laser Engineering, 2021, 50(11): 20210075

Download Citation

Tools

Save the article for my favorites

Paper Information