Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 819-833, 2018.

Cited by: 100|Bibtex|Views55|Links
EI WOS
Keywords:
Image segmentationFeature extractionSemanticsDetectorsMachine learningMore(2+)

Abstract:

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 multi-scale contour detection and it uses a novel sparse...More

Code:

Data:

Your rating :
0

 

Tags
Comments