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

Additional URL

https://doi.org/10.1109/ICIP.2017.8296501

This document is currently not available here.

Share

COinS