Abstract

We develop a deep learning algorithm for contour de-tection with a fully convolutional encoder-decoder network.Different from previous low-level edge detection, our al-gorithm focuses on detecting higher-level object contours.Our network is trained end-to-end on PASCAL VOC withrefined ground truth from inaccurate polygon annotations,yielding much higher precision in object contour detectionthan 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, ourmethod 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).