Domain Adaptation Semantic Segmentation for Urban Scene Combining Self-ensembling and Adversarial Learning

被引：0

作者：

Zhang G. ^{[1
]}

Lu F. ^{[1
]}

Long B. ^{[1
]}

Miao J. ^{[1
]}

机构：

[1] Institute of Computer Vision, Nanchang Hangkong University, Nanchang

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2021年 / 34卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Adversarial Learning; Domain Adaptation; Self-ensembling; Semantic Segmentation; Urban Scene;

D O I：

10.16451/j.cnki.issn1003-6059.202101006

中图分类号：

学科分类号：

摘要：

Aiming at the problem of high cost of urban scene label acquisition, an algorithm of domain adaptation semantic segmentation for urban scene combining self-ensembling and adversarial learning is proposed. For the inter-domain gap between source and target domains, the method of style transfer is employed to transfer the source domain into a new dataset with the style of target domain. For the problem of intra-domain gap in the target domain, the self-ensembling method is introduced and a teacher network is constructed. The teacher network is utilized to supervise and guide the student network through consistency constraints on the target domain segmentation map to reduce the intra-domain gap of the target domain and improve the segmentation accuracy. The self-training method is exploited to obtain the pseudo label of the target domain and add the pseudo label into the adversarial learning method to retrain the network and further improve the segmentation ability. Experiments on segmentation datasets verify the effectiveness of the proposed algorithm. © 2021, Science Press. All right reserved.

引用

页码：58 / 67

页数：9

共 28 条

[11]

ZOU Y, YU Z D, KUMAR B V, Et al., Unsupervised Domain Adaptation for Semantic Segmentation via Class Balanced Self-training, Proc of the European Conference on Computer Vision, pp. 289-305, (2018)

[12]

ZOU Y, YU Z D, LIU X F, Et al., Confidence Regularized Self-training, Proc of the IEEE/CVF International Conference on Computer Vision, pp. 5982-5991, (2019)

[13]

LI Y S, YUAN L, VASCONCELOS N., Bidirectional Learning for Domain Adaptation of Semantic Segmentation, Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6936-6945, (2019)

[14]

TARVAINEN A, VALPOLA H., Mean Teachers Are Better Role Models: Weight-Averaged Consistency Targets Improve Semi-supervised Deep Learning Results, Advances on Neural Information Proce-ssing Systems, 30, pp. 1195-1204, (2017)

[15]

YU L Q, WANG S J, LI X M, Et al., Uncertainty-Aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation, Proc of the International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 605-613, (2019)

[16]

XU Y H, DU B, ZHANG L F, Et al., Self-ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation, Proc of the AAAI Conference on Artificial Intelligence, pp. 5581-5588, (2019)

[17]

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, Et al., Ge-nerative Adversarial Nets, Proc of the 27th International Confe-rence on Neural Information Processing Systems, pp. 2672-2680, (2014)

[18]

ZHU J Y, PARK T, ISOLA P, Et al., Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks, Proc of the IEEE International Conference on Computer Vision, pp. 2242-2251, (2017)

[19]

TSAI Y, HUNG W, SCHULTER S, Et al., Learning to Adapt Structured Output Space for Semantic Segmentation, Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7472-7481, (2018)

[20]

LUO Y W, ZHENG L, GUAN T, Et al., Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation, Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2502-2511, (2019)

← 1 2 3 →