Convolutional Oriented Boundaries
ECCV, pp. 580-596, 2016.
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for contour detection and it uses a novel sparse boundary ...More
PPT (Upload PPT)