Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

Details Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

2012-02-10

arxiv.org/abs/1202.2160v1

Computer Science

Computer Vision and Pattern Recognition

9 pages, 4 figures

Scientific paper

Scene parsing, or semantic segmentation, consists in labeling each pixel in an image with the category of the object it belongs to. It is a challenging task that involves the simultaneous detection, segmentation and recognition of all the objects in the image. The scene parsing method proposed here starts by computing a tree of segments from a graph of pixel dissimilarities. Simultaneously, a set of dense feature vectors is computed which encodes regions of multiple sizes centered on each pixel. The feature extractor is a multiscale convolutional network trained from raw pixels. The feature vectors associated with the segments covered by each node in the tree are aggregated and fed to a classifier which produces an estimate of the distribution of object categories contained in the segment. A subset of tree nodes that cover the image are then selected so as to maximize the average "purity" of the class distributions, hence maximizing the overall likelihood that each segment will contain a single object. The convolutional network feature extractor is trained end-to-end from raw pixels, alleviating the need for engineered features. After training, the system is parameter free. The system yields record accuracies on the Stanford Background Dataset (8 classes), the Sift Flow Dataset (33 classes) and the Barcelona Dataset (170 classes) while being an order of magnitude faster than competing approaches, producing a 320 \times 240 image labeling in less than 1 second.

Affiliated with

Also associated with

No associations

Rating

Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-274250