FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

The guidance scale of the diffusion model is set as 2.0, and the sampling step is 50. For synthetic pre-training, we adopt exactly the same training protocols as real images. Then, during fine-tuning, the base learning rate is decayed to be half of the normal learning rate. Since our whole model parameters are pre-trained with synthetic images, the fine-tuning learning rate is the same throughout the whole model. The model is pre-trained and fine-tuned for the same iterations as real images.