Region average pooling for context-aware object detection
Object detection has been a key task in computer vision with deep convolutional neural networks being a significant performer. We propose a method named Region Average Pooling that leverages object co-occurrence to improve object detection performance. Given regions of interest in an image, our meth...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2017
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4072 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-5075 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-50752018-07-20T02:36:07Z Region average pooling for context-aware object detection KUAN, Kingsley MANEK, Gaurav LIN, Jie FANG, Yuan CHANDRASEKHAR, Vijay Object detection has been a key task in computer vision with deep convolutional neural networks being a significant performer. We propose a method named Region Average Pooling that leverages object co-occurrence to improve object detection performance. Given regions of interest in an image, our method augments object detection networks with pooled contextual features from other regions of interest in the scene. We implement our scheme and evaluate it on the Pascal Visual Object Classes (VOC) 2007 and Microsoft Common Objects in Context (MS COCO) datasets. When used as part of the Faster R-CNN object detection framework with VGG-16, we show an increase in mAP from 24.2% to 25.5% over baseline Faster R-CNN and Global Average Pooling when testing on MS COCO. 2017-08-20T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/4072 info:doi/10.1109/ICIP.2017.8296501 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Pooling CNN Faster R-CNN Context Object Detection Object Co-occurrence Databases and Information Systems 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 |
Pooling CNN Faster R-CNN Context Object Detection Object Co-occurrence Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Pooling CNN Faster R-CNN Context Object Detection Object Co-occurrence Databases and Information Systems Graphics and Human Computer Interfaces KUAN, Kingsley MANEK, Gaurav LIN, Jie FANG, Yuan CHANDRASEKHAR, Vijay Region average pooling for context-aware object detection |
description |
Object detection has been a key task in computer vision with deep convolutional neural networks being a significant performer. We propose a method named Region Average Pooling that leverages object co-occurrence to improve object detection performance. Given regions of interest in an image, our method augments object detection networks with pooled contextual features from other regions of interest in the scene. We implement our scheme and evaluate it on the Pascal Visual Object Classes (VOC) 2007 and Microsoft Common Objects in Context (MS COCO) datasets. When used as part of the Faster R-CNN object detection framework with VGG-16, we show an increase in mAP from 24.2% to 25.5% over baseline Faster R-CNN and Global Average Pooling when testing on MS COCO. |
format |
text |
author |
KUAN, Kingsley MANEK, Gaurav LIN, Jie FANG, Yuan CHANDRASEKHAR, Vijay |
author_facet |
KUAN, Kingsley MANEK, Gaurav LIN, Jie FANG, Yuan CHANDRASEKHAR, Vijay |
author_sort |
KUAN, Kingsley |
title |
Region average pooling for context-aware object detection |
title_short |
Region average pooling for context-aware object detection |
title_full |
Region average pooling for context-aware object detection |
title_fullStr |
Region average pooling for context-aware object detection |
title_full_unstemmed |
Region average pooling for context-aware object detection |
title_sort |
region average pooling for context-aware object detection |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2017 |
url |
https://ink.library.smu.edu.sg/sis_research/4072 |
_version_ |
1770574240090685440 |