Title | ||
---|---|---|
A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment |
Abstract | ||
---|---|---|
Domain adaptation methods in machine learning deal with the domain shift issue by aligning source and target data representation. This paper proposes a novel domain adaptation method for semantic segmentation that exploits the Fourier transform on chromatic space to improve the quality of style transfer, and generates pseudo-labels for self-training by combining the results from different teachers obtained at different rounds of self-training. Our method also applies class-level adversarial learning to achieve a more fine-grained alignment between the two domains, and a late fusion with a depth-estimation model to improve its segmentation outputs. Experiments show that our method yields superior performance in terms of accuracy compared to other existing state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/ACCESS.2022.3205414 | IEEE ACCESS |
Keywords | DocType | Volume |
Semantics, Training data, Image segmentation, Adaptation models, Estimation, Data models, Task analysis, Deep learning, adversarial learning, style transfer, semantic segmentation, domain adaptation | Journal | 10 |
ISSN | Citations | PageRank |
2169-3536 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kieu Dang Nam | 1 | 0 | 0.34 |
Tu M. Nguyen | 2 | 0 | 0.34 |
Trinh Dieu | 3 | 0 | 0.34 |
Muriel Visani | 4 | 0 | 0.34 |
Thi-Oanh Nguyen | 5 | 0 | 0.34 |
Dinh Viet Sang | 6 | 0 | 0.34 |