Image segmentation

Pattern recognition (psychology)

Invariant (physics)

Overfitting

Domain adaptation

Mathematics

Mathematical physics

Texture synthesis

Politics

Image (mathematics)

Macroeconomics

Political science

Artificial intelligence

Synthetic data

Economics

Representation (politics)

Texture (cosmology)

Stylized fact

Computer science

Computer vision

Artificial neural network

Image texture

Segmentation

Classifier (UML)

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.

Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation