Exploiting generative models in discriminative classifiers
Proceedings of the 1998 conference on Advances in neural information processing systems II
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
Sparse Multinomial Logistic Regression: Fast Algorithms and Generalization Bounds
IEEE Transactions on Pattern Analysis and Machine Intelligence
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
LOCUS: Learning Object Classes with Unsupervised Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
A Hierarchical Field Framework for Unified Context-Based Classification
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Shape Guided Object Segmentation
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
International Journal of Computer Vision
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Adapted vocabularies for generic visual categorization
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
International Journal of Computer Vision
Object Recognition by Sequential Figure-Ground Ranking
International Journal of Computer Vision
Semantic image segmentation using visible and near-infrared channels
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
On the use of regions for semantic image segmentation
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Markov random fields for sketch based video retrieval
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Sparse reconstruction for weakly supervised semantic segmentation
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition
International Journal of Computer Vision
Efficient semantic image segmentation with multi-class ranking prior
Computer Vision and Image Understanding
| Hi-index | 0.00 |
We consider the problem of semantic segmentation, i.e. assigning each pixel in an image to a set of pre-defined semantic object categories. State-of-the-art semantic segmentation algorithms typically consist of three components: a local appearance model, a local consistency model and a global consistency model. These three components are generally integrated into a unified probabilistic framework. While it enables at training time a joint estimation of the model parameters and while it ensures at test time a globally consistent labeling of the pixels, it also comes at a high computational cost.We propose a simple approach to semantic segmentation where the three components are decoupled (this journal submission is an extended version of the following conference paper: G. Csurka and F. Perronnin, "A simple high performance approach to semantic segmentation", BMVC, 2008). For the local appearance model, we make use of the Fisher kernel. While this framework was shown to lead to high accuracy for image classification, to our best knowledge this is its first application to the segmentation problem. The semantic segmentation process is then guided by a low-level segmentation which enforces local consistency. Finally, to enforce image-level consistency we use global image classifiers: if an image as a whole is unlikely to contain an object class, then the corresponding class is not considered in the segmentation pipeline.The decoupling of the components makes our system very efficient both at training and test time. An efficient training enables to estimate the model parameters on large quantities of data. Especially, we explain how our system can leverage weakly labeled data, i.e. images for which we do not have pixel-level labels but either object bounding boxes or even only image-level labels.We believe that an important contribution of this paper is to show that even a simple decoupled system can provide state-of-the-art performance on the PASCAL VOC 2007, PASCAL VOC 2008 and MSRC 21 datasets.