SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES

檔案

本條目沒有附加檔案。

日期

2019-01-01

期刊名稱

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)

卷期與頁次

頁 1870–1874

ISSN

1522-4880

ISBN

978-1-5386-6249-6

語言

英文

摘要

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).

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

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

BibTeX RIS

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