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...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 193 - 202
Main Authors Jimei Yang, Price, Brian, Cohen, Scott, Honglak Lee, Ming-Hsuan Yang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Decoding
Image edge detection
Image segmentation
Labeling
Proposals
Semantics
Training
Online AccessGet full text
ISSN1063-6919
DOI10.1109/CVPR.2016.28

Cover

More Information
Summary: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 precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (~1660 per image).
ISSN:1063-6919
DOI:10.1109/CVPR.2016.28