Pushing the Boundaries of Boundary Detection using Deep Learning
Iasonas Kokkinos Affiliation: Center for Visual Computing Affiliation: CentraleSupélec and INRIA Affiliation: Chatenay-Malabry, 92095, France Email:
Abstract
In this work we show that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection.
原文 arXiv:1511.07386;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1511.07386v2