Semantic contours from inverse detectors

Bharath Hariharan; Pablo Arbeláez; Lubomir Bourdev; Subhransu Maji; Jitendra Malik

doi:10.1109/iccv.2011.6126343

Abstract

Westudythechallengingproblemoflocalizingandclassifying category-specific object contours in real world images. For this purpose, we present a simple yet effective methodforcombininggenericobjectdetectorswithbottomup contours to identify object contours. We also provide a principledwayofcombininginformationfromdifferentpart detectors and across categories. Inorder tostudy theproblem and evaluate quantitatively our approach, we present a dataset of semantic exterior boundaries on more than 20,000 object instances belonging to 20 categories, using theimages from theVOC2011 PASCAL challenge [7].

Keywords

Pascal (unit)Computer scienceObject (grammar)Object detectionDetectorArtificial intelligenceComputer visionInverseInverse problemPattern recognition (psychology)MathematicsGeometry

Affiliated Institutions

Related Publications

Layered object detection for multi-class segmentation

Yi Yang , Sam Hallman , Deva Ramanan +1 more

We formulate a layered model for object detection and multi-class segmentation. Our system uses the output of a bank of object detectors in order to define shape priors for supp...

2010 98 citations

ConceptLearner: Discovering visual concepts from weakly labeled image collections

Bolei Zhou , Vignesh Jagadeesh , Robinson Piramuthu

Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition systems, since it is expensive to obtain fully labeled data for a large ...

2015 40 citations

Building high-level features using large scale unsupervised learning

Marc’Aurelio Ranzato , Rajat Monga , Matthieu Devin +5 more

We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabe...

2012 International Conference on Machine L... 667 citations

How good are detection proposals, really?

Jan Hosang , Rodrigo Benenson , Bernt Schiele

Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. De...

2014 arXiv (Cornell University) 56 citations

A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

Rob Fergus , Pietro Perona , Andrew Zisserman

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images ...

2005 266 citations

Publication Info

Year: 2011
Type: article
Citations: 1695
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Semantic contours from inverse detectors

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1695

OpenAlex

Cite This

APA Style

                            
                                    Bharath Hariharan, 
                                
                                    Pablo Arbeláez, 
                                
                                    Lubomir Bourdev
                                
                                et al.
                            
                            (2011). 
                            Semantic contours from inverse detectors. 
                            
                            .
                            https://doi.org/10.1109/iccv.2011.6126343

Identifiers

DOI: 10.1109/iccv.2011.6126343