Deep Crisp Boundaries: From Boundaries to Higher-level Tasks

Edge detection has 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 stateof-the-art methods when using more strict criteria. We further demonstrate the benefit of crisp edge maps for estimating optical flow, generating object proposals and semantic segmentation. In addition, the proposed refinement architecture can be easily generalized to saliency detection task, achieving state-of-art results on five commonly used saliency detection benchmark.