Abstract
Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). These ConvNet based edge detectors have approached human level performance on standard benchmarks. We provide a systematical study of these detector outputs. We show that the detection results did not accurately localize edge pixels, which can be adversarial for tasks that require crisp edge inputs. As a remedy, we propose a novel refinement architecture to address the challenging problem of learning a crisp edge detector using ConvNet. Our method leverages a top-down backward refinement pathway, and progressively increases the resolution of feature maps to generate crisp edges. Our results achieved superior performance, surpassing human accuracy when using standard criteria on BSDS500, and largely outperforming state-of-the-art methods when using more strict criteria. More importantly, we demonstrate the benefit of crisp edge maps for several important applications in computer vision, including optical flow estimation, object proposal generation and semantic segmentation.
Abstract (translated)
在深度卷积网络(ConvNet)的帮助下,边缘检测取得了重大进展。这些基于ConvNet的边缘检测器已经在标准基准测试中达到了人类级别的性能。我们对这些探测器输出进行了系统研究。我们表明,检测结果没有准确地定位边缘像素,这对于需要清晰边缘输入的任务来说可能是对抗性的。作为补救措施,我们提出了一种新颖的改进架构,以解决使用ConvNet学习清晰边缘检测器的挑战性问题。我们的方法利用自上而下的向后细化路径,逐步提高要素图的分辨率以生成清晰的边缘。我们的结果取得了卓越的性能,在BSDS500上使用标准标准时超越了人类的准确性,并且在使用更严格的标准时大大超过了最先进的方法。更重要的是,我们展示了清晰边缘图对计算机视觉中几个重要应用的好处,包括光流估计,对象建议生成和语义分割。
URL
https://arxiv.org/abs/1801.02439