Zhang, Xiaohong;
Chen, Yi;
Shen, Ziyi;
Shen, Yuming;
Zhang, Haofeng;
Zhang, Yudong;
(2022)
Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation.
IEEE Transactions on Intelligent Transportation Systems
10.1109/TITS.2022.3140481.
(In press).
Preview |
Text
Confidence-and-Refinement_Adaptation_Model_for_Cross-Domain_Semantic_Segmentation.pdf - Accepted Version Download (5MB) | Preview |
Abstract
With the rapid development of convolutional neural networks (CNNs), significant progress has been achieved in semantic segmentation. Despite the great success, such deep learning approaches require large scale real-world datasets with pixel-level annotations. However, considering that pixel-level labeling of semantics is extremely laborious, many researchers turn to utilize synthetic data with free annotations. But due to the clear domain gap, the segmentation model trained with the synthetic images tends to perform poorly on the real-world datasets. Unsupervised domain adaptation (UDA) for semantic segmentation recently gains an increasing research attention, which aims at alleviating the domain discrepancy. Existing methods in this scope either simply align features or the outputs across the source and target domains or have to deal with the complex image processing and post-processing problems. In this work, we propose a novel multi-level UDA model named Confidence-and-Refinement Adaptation Model (CRAM), which contains a confidence-aware entropy alignment (CEA) module and a style feature alignment (SFA) module. Through CEA, the adaptation is done locally via adversarial learning in the output space, making the segmentation model pay attention to the high-confident predictions. Furthermore, to enhance the model transfer in the shallow feature space, the SFA module is applied to minimize the appearance gap across domains. Experiments on two challenging UDA benchmarks ``GTA5-to-Cityscapes'' and ``SYNTHIA-to-Cityscapes'' demonstrate the effectiveness of CRAM. We achieve comparable performance with the existing state-of-the-art works with advantages in simplicity and convergence speed.
| Type: | Article |
|---|---|
| Title: | Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TITS.2022.3140481 |
| Publisher version: | https://doi.org/10.1109/TITS.2022.3140481 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | Semantic segmentation, unsupervised domain adaptation, style feature alignment, confidence-aware entropy alignment. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10147106 |
Archive Staff Only
 |
View Item |
