2023
DOI: 10.48550/arxiv.2301.13361
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation

Abstract: Recently, self-training and active learning have been proposed to alleviate this problem. Self-training can improve model accuracy with massive unlabeled data, but some pseudo labels containing noise would be generated with limited or imbalanced training data. And there will be suboptimal models if human guidance is absent. Active learning can select more effective data to intervene, while the model accuracy can not be improved because the massive unlabeled data are not used. And the probability of querying su… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 60 publications
0
1
0
Order By: Relevance
“…Many methods (such as LC [14] and DRANet [15]) use GTA5 and Cityscapes as source and target domain, respectively, for unsupervised domain adaptation tasks. Compared with some methods, such as [47,48] which completed 13 classes of SYNTHIA [49] to the Cityscapes [46] task, our 19 classes task was more complex and better reflected the performance of domain adaptation.…”
Section: Datasetmentioning
confidence: 99%
“…Many methods (such as LC [14] and DRANet [15]) use GTA5 and Cityscapes as source and target domain, respectively, for unsupervised domain adaptation tasks. Compared with some methods, such as [47,48] which completed 13 classes of SYNTHIA [49] to the Cityscapes [46] task, our 19 classes task was more complex and better reflected the performance of domain adaptation.…”
Section: Datasetmentioning
confidence: 99%