Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3158 - 3165
• Main Authors: Lim, Joseph J., Zitnick, C. Lawrence, Dollar, Piotr
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Accuracy; Detectors; Feature extraction; Image color analysis; Image edge detection; Object detection; Training
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2013.406

We propose a novel approach to both learning and detecting local contour-based representations for mid-level features. Our features, called sketch tokens, are learned using supervised mid-level information in the form of hand drawn contours in images. Patches of human generated contours are clustered to form sketch token classes and a random forest classifier is used for efficient detection in novel images. We demonstrate our approach on both top-down and bottom-up tasks. We show state-of-the-art results on the top-down task of contour detection while being over 200x faster than competing methods. We also achieve large improvements in detection accuracy for the bottom-up tasks of pedestrian and object detection as measured on INRIA and PASCAL, respectively. These gains are due to the complementary information provided by sketch tokens to low-level features such as gradient histograms.