Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Jinhong Deng"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:472-480
Source-Free Unsupervised Domain Adaptation(SFUDA) aims to adapt a pre-trained source model to an unlabeled target domain without access to the original labeled source domain samples. Many existing SFUDA approaches apply the self-training strategy, wh
Publikováno v:
IEEE Signal Processing Letters. 29:2203-2207
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution. However, the label shift issue is unfortunately overlooked,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e0bc2ad055ff394050da76baf2aa5d5
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197864
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f56bbc38437bbaa755e53ec98f301db4
https://doi.org/10.1007/978-3-031-19787-1_30
https://doi.org/10.1007/978-3-031-19787-1_30
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Publikováno v:
CVPR
Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe1712278e0f6ce325c1283bac7777ef
http://arxiv.org/abs/2003.00707
http://arxiv.org/abs/2003.00707