Finding Things: Image Parsing with Regions and Per-Exemplar Detectors
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3001-3008
- https://doi.org/10.1109/cvpr.2013.386
Abstract
This paper presents a system for image parsing, or labeling each pixel in an image with its semantic category, aimed at achieving broad coverage across hundreds of object categories, many of them sparsely sampled. The system combines region-level features with per-exemplar sliding window detectors. Per-exemplar detectors are better suited for our parsing task than traditional bounding box detectors: they perform well on classes with little training data and high intra-class variation, and they allow object masks to be transferred into the test image for pixel-level segmentation. The proposed system achieves state-of-the-art accuracy on three challenging datasets, the largest of which contains 45,676 images and 232 labels.Keywords
This publication has 16 references indexed in Scilit:
- SuperparsingInternational Journal of Computer Vision, 2012
- Beyond the Line of Sight: Labeling the Underlying SurfacesLecture Notes in Computer Science, 2012
- Ensemble of exemplar-SVMs for object detection and beyondPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Accurate Object Recognition with Shape MasksInternational Journal of Computer Vision, 2011
- Nonparametric Scene Parsing via Label TransferIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Efficient hierarchical graph-based video segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Combining Appearance and Structure from Motion Features for Road Scene UnderstandingPublished by British Machine Vision Association and Society for Pattern Recognition ,2009
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- What energy functions can be minimized via graph cuts?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004