Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 819-833, 2018.
Image segmentationFeature extractionSemanticsDetectorsMachine learningMore(2+)
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
Full Text (Upload PDF)
PPT (Upload PPT)