Abstract
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by aggregating histograms in the neighborhood of each superpixel and then refine our results further by using the classifier in a conditional random field operating on the superpixel graph. Our proposed method exceeds the previously published state-of-the-art on two challenging datasets: Graz-02 and the PASCAL VOC 2007 Segmentation Challenge.
Keywords
Artificial intelligenceConditional random fieldHistogramClassifier (UML)Pattern recognition (psychology)SegmentationComputer sciencePascal (unit)PixelComputer visionImage segmentationObject detectionImage (mathematics)
Affiliated Institutions
Related Publications
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that...
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...
Learning Deconvolution Network for Semantic Segmentation
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer ne...
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large- scale visual recognition challenge (ILSVRC2012). The success o...
Publication Info
- Year
- 2009
- Type
- article
- Pages
- 670-677
- Citations
- 649
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
649
OpenAlex
Cite This
Brian Fulkerson,
Andrea Vedaldi,
Stefano Soatto
(2009).
Class segmentation and object localization with superpixel neighborhoods.
, 670-677.
https://doi.org/10.1109/iccv.2009.5459175
Identifiers
- DOI
- 10.1109/iccv.2009.5459175