Object Contour Detection with a Fully Convolutional Encoder-Decoder Network


We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher… (More)
DOI: 10.1109/CVPR.2016.28


12 Figures and Tables


Citations per Year

66 Citations

Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.