paper-with-me

홈 › Papers

IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels

2022-10-07 · XueWei Li, Weilun Zhang, Jie Gao, Xuzhou Fu, Jian Yu

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods.

📄 PDF Abstract BibTeX arXiv:2210.03435

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationPseudo LabelSegmentationSemantic SegmentationSubdomain adaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Pixel-level Intra-domain Adaptation for Semantic Segmentation

2021-10-17 · ACM International Conference on Multimedia 2021 10 · Zizheng Yan, Xianggang Yu, Yipeng Qin, Yushuang Wu 외

Recent advances in unsupervised domain adaptation have achieved remarkable performance on semantic segmentation tasks. Despite such progress, existing works mainly focus on bridging the inter-domain gaps between the sour…

Domain AdaptationSegmentationSemantic SegmentationSynthetic-to-Real Translation+1

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

2021-12-11 · Mohammadreza Ghorvei, Mohammadreza Kavianpour, Mohammad TH Beheshti, Amin Ramezani

Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the dat…

Domain AdaptationFault DiagnosisSubdomain adaptationUnsupervised Domain Adaptation

Deep Subdomain Adaptation Network for Image Classification

2021-06-17 · Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Guolin Ke 외

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the gl…

ClassificationDomain Adaptationimage-classificationImage Classification+3

ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation

2022-07-19 · Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim 외

Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the labeled source domain and the unla…

Domain AdaptationSemantic Segmentation

Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images

2021-08-28 · Lefei Zhang, Meng Lan, Jing Zhang, DaCheng Tao

Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. Deep neural networks have advanced this field by leveraging the power of large-scale labeled data, which, how…

Domain AdaptationRoad SegmentationUnsupervised Domain Adaptation