SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
1874 | en_US |
dc.citation.spage |
1870 | en_US |
dc.citation.woscount |
0 | en_US |
dc.contributor.author |
Lin, Yong-Xiang | en_US |
dc.contributor.author |
Tan, Daniel Stanley | en_US |
dc.contributor.author |
Cheng, Wen-Huang | en_US |
dc.contributor.author |
Chen, Yung-Yao | en_US |
dc.contributor.author |
Hua, Kai-Lung | en_US |
dc.contributor.department |
電子工程學系及電子研究所 | zh_TW |
dc.contributor.department |
Department of Electronics Engineering and Institute of Electronics | en_US |
dc.date.accessioned |
2020-05-05T00:01:59Z | |
dc.date.available |
2020-05-05T00:01:59Z | |
dc.date.issued |
2019-01-01 | en_US |
dc.description.abstract |
It is very expensive and time consuming to collect a large enough dataset with pixel-level annotations to train a semantic segmentation model. Synthetic datasets are common alternatives for training segmentation models, however models trained on synthetic data do not necessarily perform well on real world images due to the domain shift problem. Domain adaptation techniques address this problem by leveraging on adversarial training to align features. Prior works have mostly performed global feature alignment. They do not consider the positions of objects. However, objects in urban scenes are highly correlated with their spatial locations. For example, the sky will always appear on top while cars will usually appear in the middle of the image. Based on this insight, we propose a spatial-aware discriminator that accounts for the spatial prior on the objects in order to improve the feature alignment. We demonstrate in our experiments that our model outperforms several state-of-the-art baselines in terms of mean intersection over union (mIoU). | en_US |
dc.identifier.isbn |
978-1-5386-6249-6 | en_US |
dc.identifier.issn |
1522-4880 | en_US |
dc.identifier.journal |
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/154044 | |
dc.identifier.wosnumber |
WOS:000521828601200 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Semantic segmentation | en_US |
dc.subject |
Domain adaptation | en_US |
dc.subject |
Spatial Structure | en_US |
dc.title |
SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文
引用此條目
Lin, Y.-X., Tan, D. S., Cheng, W.-H., Chen, Y.-Y., & Hua, K.-L. (2019). SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 1870–1874. https://ir.lib.nycu.edu.tw/handle/11536/154044
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/154044