Convolutional Oriented Boundaries

08/09/2016 ∙ by Kevis-Kokitsi Maninis, et al. ∙ 0

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 representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments on BSDS, PASCAL Context, PASCAL Segmentation, and MS-COCO, showing that COB provides state-of-the-art contours, region hierarchies, and object proposals in all datasets.



There are no comments yet.


page 2

page 4

page 7

page 8

page 14

Code Repositories


Multiscale Combinatorial Grouping - Object Proposals and Segmentation

view repo


Convolutional Oriented Boundaries

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.