Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Changjae | - |
dc.contributor.author | Lee, Seunghun | - |
dc.contributor.author | Im, Sunghoon | - |
dc.date.accessioned | 2024-02-06T16:10:17Z | - |
dc.date.available | 2024-02-06T16:10:17Z | - |
dc.date.created | 2024-02-06 | - |
dc.date.issued | 2023-11-22 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/47800 | - |
dc.description.abstract | In this paper, we present a novel multi-target domain adaptation (MTDA) method that adapts a single model to multiple domains with class-wise attribute transfer. To achieve this, we propose a high-precision pseudo labeling method for target domain images by utilizing cross-domain correspondence matching, which matches a target region to the most similar source region. Then, we propose class-wise image translation using the pseudo labels to avoid the problem of transferring characteristics between different classes and to allow translation between the same classes. Lastly, we introduce cross-domain feature consistency to learn the different characteristics of each target domain. Extensive experiments on the various complex driving scene show that ours achieves better performance than other state-of-the-art methods. The dense ablation study demonstrates the effectiveness of the proposed method. © 2023. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. | - |
dc.language | English | - |
dc.publisher | The British Machine Vision Association and Society for Pattern Recognition | - |
dc.title | Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation | - |
dc.type | Conference Paper | - |
dc.identifier.bibliographicCitation | British Machine Vision Conference, pp.1 - 13 | - |
dc.identifier.url | https://proceedings.bmvc2023.org/633/ | - |
dc.citation.conferencePlace | UK | - |
dc.citation.conferencePlace | Aberdeen | - |
dc.citation.endPage | 13 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | British Machine Vision Conference | - |
poster_Class_Wise_Attribute_Transfer_BMVC23.pdf
기타 데이터 / 0 B / Adobe PDF downloadpaper_Class_Wise_Attribute_Transfer_BMVC23.pdf
기타 데이터 / 0 B / Adobe PDF download