A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment
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.
PDF Abstract
SYNTHIA
GTA5
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Domain Adaptation | GTA5 to Cityscapes | FAFS | mIoU | 58.8 | # 17 | |
| Unsupervised Domain Adaptation | GTAV-to-Cityscapes Labels | FAFS | mIoU | 58.8 | # 14 | |
| Unsupervised Domain Adaptation | SYNTHIA-to-Cityscapes | FAFS | mIoU (13 classes) | 61.4 | # 12 | |
| mIoU | 54.5 | # 8 |
