Region average pooling for context-aware object detection
Publication Type
Conference Proceeding Article
Publication Date
8-2017
Abstract
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.
Keywords
Pooling, CNN, Faster R-CNN, Context, Object Detection, Object Co-occurrence
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
2017 IEEE International Conference on Image Processing proceedings: 17-20 September, Beijing, China
First Page
1347
Last Page
1351
ISBN
9781509021758
Identifier
10.1109/ICIP.2017.8296501
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
KUAN, Kingsley; MANEK, Gaurav; LIN, Jie; FANG, Yuan; and CHANDRASEKHAR, Vijay.
Region average pooling for context-aware object detection. (2017). 2017 IEEE International Conference on Image Processing proceedings: 17-20 September, Beijing, China. 1347-1351.
Available at: https://ink.library.smu.edu.sg/sis_research/4072
Additional URL
https://doi.org/10.1109/ICIP.2017.8296501