التفاصيل البيبلوغرافية
| العنوان: |
Uncertainty-aware consistency regularization for cross-domain semantic segmentation. |
| المؤلفون: |
Zhou, Qianyu, Feng, Zhengyang, Gu, Qiqi, Cheng, Guangliang, Lu, Xuequan, Shi, Jianping, Ma, Lizhuang |
| المصدر: |
Computer Vision & Image Understanding; Aug2022, Vol. 221, pN.PAG-N.PAG, 1p |
| مصطلحات موضوعية: |
TRANSFER students, TRANSFER of students |
| مستخلص: |
Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model. Besides, the local regional consistency in UDA has been largely neglected, and only extracting the global-level pattern information is not powerful enough for feature alignment due to the abuse use of contexts. To this end, we propose an uncertainty-aware consistency regularization method for cross-domain semantic segmentation. Firstly, we introduce an uncertainty-guided consistency loss with a dynamic weighting scheme by exploiting the latent uncertainty information of the target samples. As such, more meaningful and reliable knowledge from the teacher model can be transferred to the student model. We further reveal the reason why the current consistency regularization is often unstable in minimizing the domain discrepancy. Besides, we design a ClassDrop mask generation algorithm to produce strong class-wise perturbations. Guided by this mask, we propose a ClassOut strategy to realize effective regional consistency in a fine-grained manner. Experiments demonstrate that our method outperforms the state-of-the-art methods on four domain adaptation benchmarks, i.e., GTAV → Cityscapes, SYNTHIA → Cityscapes, Virtual KITTI ⟶ KITTI and Cityscapes ⟶ KITTI. • We propose an uncertainty-aware consistency regularization framework for cross-domain semantic segmentation. • We present an uncertainty-guided consistency loss to alleviate the error accumulation. Besides, we develop a ClassOut strategy to keep the local regional consistency under the guidance of strong class-wise perturbations. • We achieve the state-of-the-art performance on four challenging benchmark datasets of UDA. [ABSTRACT FROM AUTHOR] |
|
Copyright of Computer Vision & Image Understanding is the property of Academic Press Inc. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Supplemental Index |
