论文标题
segfix：分割的模型 - 不足的边界细节
SegFix: Model-Agnostic Boundary Refinement for Segmentation
论文作者
论文摘要
We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model. Motivated by the empirical observation that the label predictions of interior pixels are more reliable, we propose to replace the originally unreliable predictions of boundary pixels by the predictions of interior pixels. Our approach processes only the input image through two steps: (i) localize the boundary pixels and (ii) identify the corresponding interior pixel for each boundary pixel.我们通过学习从边界像素到内部像素的方向来构建对应关系。我们的方法不需要先前的细分模型信息，并且几乎实现了实时速度。 We empirically verify that our SegFix consistently reduces the boundary errors for segmentation results generated from various state-of-the-art models on Cityscapes, ADE20K and GTA5.代码可在以下网址获得：https：//github.com/openseg-group/openseg.pytorch。
We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model. Motivated by the empirical observation that the label predictions of interior pixels are more reliable, we propose to replace the originally unreliable predictions of boundary pixels by the predictions of interior pixels. Our approach processes only the input image through two steps: (i) localize the boundary pixels and (ii) identify the corresponding interior pixel for each boundary pixel. We build the correspondence by learning a direction away from the boundary pixel to an interior pixel. Our method requires no prior information of the segmentation models and achieves nearly real-time speed. We empirically verify that our SegFix consistently reduces the boundary errors for segmentation results generated from various state-of-the-art models on Cityscapes, ADE20K and GTA5. Code is available at: https://github.com/openseg-group/openseg.pytorch.
