Sparse Dictionaries for Semantic Segmentation

@inproceedings{Tao2014SparseDF,
  title={Sparse Dictionaries for Semantic Segmentation},
  author={Lingling Tao and Fatih Murat Porikli and Ren{\'e} Vidal},
  booktitle={ECCV},
  year={2014}
}
A popular trend in semantic segmentation is to use top-down object information to improve bottom-up segmentation. For instance, the classification scores of the Bag of Features (BoF) model for image classification have been used to build a top-down categorization cost in a Conditional Random Field (CRF) model for semantic segmentation. Recent work shows that discriminative sparse dictionary learning (DSDL) can improve upon the unsupervised K-means dictionary learning method used in the BoF… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-6 of 6 extracted citations

Bilevel Model-Based Discriminative Dictionary Learning for Recognition

IEEE Transactions on Image Processing • 2017
View 4 Excerpts
Highly Influenced

CRF with locality-consistent dictionary learning for semantic segmentation

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) • 2015
View 9 Excerpts
Highly Influenced

Multi-instance object segmentation with occlusion handling

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 2 Excerpts

Top-Down Visual Saliency via Joint CRF and Dictionary Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2012

References

Publications referenced by this paper.
Showing 1-10 of 36 references

Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation

2012 IEEE Conference on Computer Vision and Pattern Recognition • 2012
View 9 Excerpts
Highly Influenced

Task-Driven Dictionary Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2012
View 4 Excerpts
Highly Influenced

Learning mid-level features for recognition

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition • 2010
View 4 Excerpts
Highly Influenced

Cutting-plane training of structural SVMs

View 7 Excerpts
Highly Influenced

The TU Graz-02 database

A. Opelt, A. Pinz
http://www.emt.tugraz.at/ pinz/data/GRAZ02/ • 2002
View 3 Excerpts
Highly Influenced

Finding Things: Image Parsing with Regions and Per-Exemplar Detectors

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 3 Excerpts

Similar Papers

Loading similar papers…