DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jinyoung | ko |
dc.contributor.author | Son, Minseok | ko |
dc.contributor.author | Lee, Sumin | ko |
dc.contributor.author | Kim, Changick | ko |
dc.date.accessioned | 2022-11-21T07:00:40Z | - |
dc.date.available | 2022-11-21T07:00:40Z | - |
dc.date.created | 2022-11-18 | - |
dc.date.created | 2022-11-18 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | IEEE International Conference on Image Processing, ICIP 2022, pp.4183 - 4187 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | http://hdl.handle.net/10203/300290 | - |
dc.description.abstract | Unsupervised domain adaptation (UDA) for semantic segmentation aims to predict class annotations on an unlabeled target dataset by training on a rich labeled source dataset. It is crucial in UDA semantic segmentation to decrease the domain gap by learning domain invariant feature representations across both domains. In this paper, we propose a novel transformer-based network, called a domain adaptive transformer (DAT), using a self-training scheme. We introduce domain invariant attention (DIA), which enables the DAT to exploit high-level domain invariant features at the patch level. Moreover, an entropy-based selective pseudo-labeling algorithm provides the DAT with reliable pseudo-labels of target samples for domain adaptive self-training, which corrects the noisy pseudo-labels online. We show that our DAT greatly improves the domain adaptability and achieves state-of-the-art results on the SYNTHIA-to-Cityscapes benchmark. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | DAT: Domain Adaptive Transformer for Domain Adaptive Semantic Segmentation | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85146677756 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 4183 | - |
dc.citation.endingpage | 4187 | - |
dc.citation.publicationname | IEEE International Conference on Image Processing, ICIP 2022 | - |
dc.identifier.conferencecountry | FR | - |
dc.identifier.conferencelocation | Bordeaux | - |
dc.identifier.doi | 10.1109/ICIP46576.2022.9897293 | - |
dc.contributor.localauthor | Kim, Changick | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.