BING: Binarized normed gradients for objectness estimation at 300fps
Training a generic objectness measure to produce object proposals has recently become of significant interest. We observe that generic objects with well-defined closed boundaries can be detected by looking at the norm of gradients, with a suitable resizing of their corresponding image windows to a s...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2014
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4803 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-5806 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-58062020-01-16T09:18:03Z BING: Binarized normed gradients for objectness estimation at 300fps CHENG, Ming-Ming LIU, Yun LIN, Wen-yan ZHANG, Ziming ROSIN, Paul L. TORR Training a generic objectness measure to produce object proposals has recently become of significant interest. We observe that generic objects with well-defined closed boundaries can be detected by looking at the norm of gradients, with a suitable resizing of their corresponding image windows to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients (BING), can be used for efficient objectness estimation, which requires only a few atomic operations (e.g., add, bitwise shift, etc.). To improve localization quality of the proposals while maintaining efficiency, we propose a novel fast segmentation method and demonstrate its effectiveness for improving BING’s localization performance, when used in multithresholding straddling expansion (MTSE) postprocessing. On the challenging PASCAL VOC2007 dataset, using 1000 proposals per image and intersectionover-union threshold of 0.5, our proposal method achieves a 95.6% object detection rate and 78.6% mean average best overlap in less than 0.005 second per image 2014-06-28T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/4803 info:doi/10.1109/CVPR.2014.414 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University object proposals objectness visual attention category agnostic proposal Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
object proposals objectness visual attention category agnostic proposal Graphics and Human Computer Interfaces |
spellingShingle |
object proposals objectness visual attention category agnostic proposal Graphics and Human Computer Interfaces CHENG, Ming-Ming LIU, Yun LIN, Wen-yan ZHANG, Ziming ROSIN, Paul L. TORR BING: Binarized normed gradients for objectness estimation at 300fps |
description |
Training a generic objectness measure to produce object proposals has recently become of significant interest. We observe that generic objects with well-defined closed boundaries can be detected by looking at the norm of gradients, with a suitable resizing of their corresponding image windows to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients (BING), can be used for efficient objectness estimation, which requires only a few atomic operations (e.g., add, bitwise shift, etc.). To improve localization quality of the proposals while maintaining efficiency, we propose a novel fast segmentation method and demonstrate its effectiveness for improving BING’s localization performance, when used in multithresholding straddling expansion (MTSE) postprocessing. On the challenging PASCAL VOC2007 dataset, using 1000 proposals per image and intersectionover-union threshold of 0.5, our proposal method achieves a 95.6% object detection rate and 78.6% mean average best overlap in less than 0.005 second per image |
format |
text |
author |
CHENG, Ming-Ming LIU, Yun LIN, Wen-yan ZHANG, Ziming ROSIN, Paul L. TORR |
author_facet |
CHENG, Ming-Ming LIU, Yun LIN, Wen-yan ZHANG, Ziming ROSIN, Paul L. TORR |
author_sort |
CHENG, Ming-Ming |
title |
BING: Binarized normed gradients for objectness estimation at 300fps |
title_short |
BING: Binarized normed gradients for objectness estimation at 300fps |
title_full |
BING: Binarized normed gradients for objectness estimation at 300fps |
title_fullStr |
BING: Binarized normed gradients for objectness estimation at 300fps |
title_full_unstemmed |
BING: Binarized normed gradients for objectness estimation at 300fps |
title_sort |
bing: binarized normed gradients for objectness estimation at 300fps |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2014 |
url |
https://ink.library.smu.edu.sg/sis_research/4803 |
_version_ |
1770575035927363584 |