arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2007.04269cs.CV
收藏

SegFix：用于分割的模型无关边界细化

SegFix: Model-Agnostic Boundary Refinement for Segmentation

Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院计算技术研究所智能信息处理重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）

Yuhui Yuan, Jingyi Xie, Xilin Chen, Jingdong Wang

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

我们提出了一个模型不可知的后处理方案，以提高边界质量的分割结果，是由任何现有的分割模型。出于经验观察，内部像素的标签预测更可靠，我们建议用内部像素的预测来取代原来不可靠的边界像素的预测。我们的方法通过两个步骤只处理输入图像：（i）定位边界像素和（ii）为每个边界像素识别相应的内部像素。我们通过学习从边界像素到内部像素的方向来建立对应关系。我们的方法不需要任何先验信息的分割模型，并达到接近实时的速度。我们通过经验验证，我们的SegFix始终减少了Cityscapes、ADE20K和GTA 5上各种最先进模型生成的分割结果的边界误差。代码可在：https://github.com/openseg-group/openseg.pytorch.

英文摘要：

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. 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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑