Deep Crisp Boundaries
Citations Over TimeTop 10% of 2017 papers
Abstract
Edge detection had made significant progress with the help of deep Convolutional Networks (ConvNet). ConvNet based edge detectors approached human level performance on standard benchmarks. We provide a systematical study of these detector outputs, and show that they failed to accurately localize edges, which can be adversarial for tasks that require crisp edge inputs. In addition, 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 achieve promising performance on BSDS500, surpassing human accuracy when using standard criteria, and largely outperforming state-of-the-art methods when using more strict criteria. We further demonstrate the benefit of crisp edge maps for estimating optical flow and generating object proposals.
Related Papers
- → R-CNN minus R(2015)68 cited
- → Design and Implementation of an Object Detection System Using Faster R-CNN(2019)20 cited
- → Image edge detection based on statistical features(2010)4 cited
- → A new prediction method for edge detection based on human visual feature(2012)3 cited
- → Edge linking using angle information(2015)