G-CNN: an Iterative Grid Based Object Detector. Najibi, M., Rastegari, M., & Davis, L. S. arXiv:1512.07729 [cs], December, 2015. arXiv: 1512.07729![G-CNN: an Iterative Grid Based Object Detector [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.
@article{najibi_g-cnn:_2015,
title = {G-{CNN}: an {Iterative} {Grid} {Based} {Object} {Detector}},
shorttitle = {G-{CNN}},
url = {http://arxiv.org/abs/1512.07729},
abstract = {We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.},
urldate = {2018-04-02TZ},
journal = {arXiv:1512.07729 [cs]},
author = {Najibi, Mahyar and Rastegari, Mohammad and Davis, Larry S.},
month = dec,
year = {2015},
note = {arXiv: 1512.07729},
keywords = {Computer Science - Computer Vision and Pattern Recognition}
}
Downloads: 0
{"_id":"SpcyhTRdbJbd3rgtm","bibbaseid":"najibi-rastegari-davis-gcnnaniterativegridbasedobjectdetector-2015","downloads":0,"creationDate":"2018-04-06T04:26:07.159Z","title":"G-CNN: an Iterative Grid Based Object Detector","author_short":["Najibi, M.","Rastegari, M.","Davis, L. S."],"year":2015,"bibtype":"article","biburl":"https://bibbase.org/zotero/alwynmathew","bibdata":{"bibtype":"article","type":"article","title":"G-CNN: an Iterative Grid Based Object Detector","shorttitle":"G-CNN","url":"http://arxiv.org/abs/1512.07729","abstract":"We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.","urldate":"2018-04-02TZ","journal":"arXiv:1512.07729 [cs]","author":[{"propositions":[],"lastnames":["Najibi"],"firstnames":["Mahyar"],"suffixes":[]},{"propositions":[],"lastnames":["Rastegari"],"firstnames":["Mohammad"],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["Larry","S."],"suffixes":[]}],"month":"December","year":"2015","note":"arXiv: 1512.07729","keywords":"Computer Science - Computer Vision and Pattern Recognition","bibtex":"@article{najibi_g-cnn:_2015,\n\ttitle = {G-{CNN}: an {Iterative} {Grid} {Based} {Object} {Detector}},\n\tshorttitle = {G-{CNN}},\n\turl = {http://arxiv.org/abs/1512.07729},\n\tabstract = {We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.},\n\turldate = {2018-04-02TZ},\n\tjournal = {arXiv:1512.07729 [cs]},\n\tauthor = {Najibi, Mahyar and Rastegari, Mohammad and Davis, Larry S.},\n\tmonth = dec,\n\tyear = {2015},\n\tnote = {arXiv: 1512.07729},\n\tkeywords = {Computer Science - Computer Vision and Pattern Recognition}\n}\n\n","author_short":["Najibi, M.","Rastegari, M.","Davis, L. S."],"key":"najibi_g-cnn:_2015","id":"najibi_g-cnn:_2015","bibbaseid":"najibi-rastegari-davis-gcnnaniterativegridbasedobjectdetector-2015","role":"author","urls":{"Paper":"http://arxiv.org/abs/1512.07729"},"keyword":["Computer Science - Computer Vision and Pattern Recognition"],"downloads":0,"html":""},"search_terms":["cnn","iterative","grid","based","object","detector","najibi","rastegari","davis"],"keywords":["computer science - computer vision and pattern recognition"],"authorIDs":[],"dataSources":["p3JdPh89hHfoARFkn"]}