PIXEL LEVEL DATA AUGMENTATION FOR SEMANTIC IMAGE SEGMENTATION USING GENERATIVE ADVERSARIAL NETWORKS

被引：0

作者：

Liu, Shuangting ^{[1
]}

Zhang, Jiaqi ^{[1
]}

Chen, Yuxin ^{[1
]}

Liu, Yifan ^{[1
]}

Qin, Zengchang ^{[1
,2
]}

Wan, Tao ^{[3
]}

机构：

[1] Beihang Univ, Sch ASEE, Intelligent Comp & Machine Learning Lab, Beijing, Peoples R China

[2] Keep Inc, Keep Labs, Beijing, Peoples R China

[3] Beihang Univ, Sch Biol Sci & Med Engn, Beijing, Peoples R China

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2019年

关键词：

Data augmentation; generative adversarial networks (GANs); semantic segmentation;

D O I：

10.1109/icassp.2019.8683590

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the semantic label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of semantic segmentation networks. Experimental results show that the proposed method can not only improve segmentation performance on those classes with low accuracy, but also obtain 1.3% to 2.1% increase in average segmentation accuracy. It shows that this augmentation method can boost the accuracy and be easily applicable to any other segmentation models.

引用

页码：1902 / 1906

页数：5

共 50 条

[1] Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks
Antoniou, Antreas
Storkey, Amos
Edwards, Harrison
[J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT III, 2018, 11141 : 594 - 603
[2] Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks
Shin, Hoo-Chang
Tenenholtz, Neil A.
Rogers, Jameson K.
Schwarz, Christopher G.
Senjem, Matthew L.
Gunter, Jeffrey L.
Andriole, Katherine P.
Michalski, Mark
[J]. SIMULATION AND SYNTHESIS IN MEDICAL IMAGING, 2018, 11037 : 1 - 11
[3] Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
Sandfort, Veit
Yan, Ke
Pickhardt, Perry J.
Summers, Ronald M.
[J]. SCIENTIFIC REPORTS, 2019, 9 (1)
[4] Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
Veit Sandfort
Ke Yan
Perry J. Pickhardt
Ronald M. Summers
[J]. Scientific Reports, 9
[5] Data Augmentation with Generative Adversarial Networks for Grocery Product Image Recognition
Wei, Yuchen
Xu, Shuxiang
Son Tran
Kang, Byeong
[J]. 16TH IEEE INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV 2020), 2020, : 963 - 968
[6] Auxiliary Conditional Generative Adversarial Networks for Image Data Set Augmentation
Mudavathu, Kalpana Devi Bai
Rao, V. P. Chandra Sekhara
Ramana, K., V
[J]. PROCEEDINGS OF THE 2018 3RD INTERNATIONAL CONFERENCE ON INVENTIVE COMPUTATION TECHNOLOGIES (ICICT 2018), 2018, : 263 - 269
[7] Conditional Generative Adversarial Networks for Data Augmentation of a Neonatal Image Dataset
Lyra, Simon
Mustafa, Arian
Rixen, Joeran
Borik, Stefan
Lueken, Markus
Leonhardt, Steffen
[J]. SENSORS, 2023, 23 (02)
[8] Data Augmentation Based on Generative Adversarial Networks for Endoscopic Image Classification
Park, Hyun-Cheol
Hong, In-Pyo
Poudel, Sahadev
Choi, Chang
[J]. IEEE ACCESS, 2023, 11 : 49216 - 49225
[9] Conditional Generative Adversarial Refinement Networks for Unbalanced Medical Image Semantic Segmentation
Rezaei, Mina
Yang, Haojin
Harmuth, Konstantin
Meinel, Christoph
[J]. 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1836 - 1845
[10] SEQUENTIAL IOT DATA AUGMENTATION USING GENERATIVE ADVERSARIAL NETWORKS
Tschuchnig, Maximilian Ernst
Ferner, Cornelia
Wegenkittl, Stefan
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 4212 - 4216

← 1 2 3 4 5 →