Segmentation As Selective Search for Object Recognition
2017-08-20 22:46
1116 查看
Segmentation As Selective Search for Object Recognition
Abstract
For object recognition, the current state-of-the-art is based on exhaustive search. However, to enable the use of more expensive features and classifiers and thereby progress beyond the state-of-the-art, a selective search strategy is needed. Therefore, we
adapt segmentation as a selective search by reconsidering segmentation: We propose to generate many approximate locations over few and precise object delineations because (1) an object whose location is never generated can not be recognised and (2) appearance
and immediate nearby context are most effective for object recognition.
Our method is class-independent and is shown to cover 96.7% of all objects in the Pascal VOC 2007 test set using only 1,536 locations per image. Our selective search enables the use of the more expensive bag-of-words method which we use to substantially improve
the state-of-the-art by up to 8.5% for 8 out of 20 classes on the Pascal VOC 2010 detection challenge.
Info
Software from this paper will become available from [url=http://koen.me/research/selectivesearch/]http://koen.me/research/selectivesearch/
Bibtex Entry
https://ivi.fnwi.uva.nl/isis/publications/bibtexbrowser.php?key=vandeSandeICCV2011&bib=all.bib
Segmentation As Selective Search for Object Recognition K. E. A. van de Sande, J. R. R. Uijlings, T. Gevers, A. W. M. Smeulders In IEEE International Conference on Computer Vision 2011. [bibtex] [pdf] |
For object recognition, the current state-of-the-art is based on exhaustive search. However, to enable the use of more expensive features and classifiers and thereby progress beyond the state-of-the-art, a selective search strategy is needed. Therefore, we
adapt segmentation as a selective search by reconsidering segmentation: We propose to generate many approximate locations over few and precise object delineations because (1) an object whose location is never generated can not be recognised and (2) appearance
and immediate nearby context are most effective for object recognition.
Our method is class-independent and is shown to cover 96.7% of all objects in the Pascal VOC 2007 test set using only 1,536 locations per image. Our selective search enables the use of the more expensive bag-of-words method which we use to substantially improve
the state-of-the-art by up to 8.5% for 8 out of 20 classes on the Pascal VOC 2010 detection challenge.
Info
Software from this paper will become available from [url=http://koen.me/research/selectivesearch/]http://koen.me/research/selectivesearch/
Bibtex Entry
@InProceedings{vandeSandeICCV2011, author = "van de Sande, K. E. A. and Uijlings, J. R. R. and Gevers, T. and Smeulders, A. W. M.", title = "Segmentation As Selective Search for Object Recognition", booktitle = "IEEE International Conference on Computer Vision", year = "2011", url = "https://ivi.fnwi.uva.nl/isis/publications/2011/vandeSandeICCV2011", pdf = "https://ivi.fnwi.uva.nl/isis/publications/2011/vandeSandeICCV2011/vandeSandeICCV2011.pdf", has_image = 1 }
https://ivi.fnwi.uva.nl/isis/publications/bibtexbrowser.php?key=vandeSandeICCV2011&bib=all.bib
相关文章推荐
- 【论文阅读笔记】Segmentation as Selective Search for Object Recognition
- 论文笔记:Segmentation as Selective Search for Object Recognition(ICCV2011)
- Segmentation as Selective Search for Object Recognition
- Selective Search for Object Recognition(阅读)
- 【学习笔记】Selective Search算法--Selective Search for Object Recognition
- Selective Search for Object Recognition解读
- R-CNN学习笔记1:Selective Search for Object Recognition
- Selective Search for Object Recognition 个人总结
- Selective Search for Object Recognition(IJCV 2013) 论文及代码解读
- 机器学习:Selective Search for Object Recognition
- 【计算机视觉】Selective Search for Object Recognition论文阅读2
- Selective Search for Object Recognition
- Selective Search for Object Recognition----论文笔记
- Selective Search for Object Recognition
- 论文笔记《Selective Search for object recognition》
- 【计算机视觉】Selective Search for Object Recognition论文阅读3
- 论文笔记《Selective Search for object recognition》
- R-CNN之前的准备:Selective Search for Object Recognition
- 论文提要“Selective Search for Object Recognition”
- 研读《Selective Search for Object Recognition》论文