Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained with synthetic data to generalize to real data. In this paper, considering the fundamental difference between the two domains as the texture, we propose a method to adapt to the target domain's texture. First, we diversity the texture of synthetic images using a style transfer algorithm. The various textures of generated images prevent a segmentation model from overfitting to one specific (synthetic) texture. Then, we fine-Tune the model with self-Training to get direct supervision of the target texture. Our results achieve state-of-The-Art performance and we analyze the properties of the model trained on the stylized dataset with extensive experiments.
|Number of pages||10|
|Journal||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Publication status||Published - 2020|
|Event||2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States|
Duration: 2020 Jun 14 → 2020 Jun 19
Bibliographical noteFunding Information:
This work was supported by the National Research Foundation of Korea grant funded by Korean government (No. NRF-2019R1A2C2003760).
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition