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. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Object Detection, CNN, Pooling, Faster R-CNN, Object Co-occurrence, Context |
Field | DocType | ISSN |
Computer vision,Object detection,Pattern recognition,Task analysis,Convolutional neural network,Computer science,Pooling,Feature extraction,Artificial intelligence | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kingsley Kuan | 1 | 21 | 1.77 |
Gaurav Manek | 2 | 23 | 2.52 |
Jie Lin | 3 | 3495 | 502.80 |
Yuan Fang | 4 | 168 | 19.74 |
Vijay Chandrasekhar | 5 | 191 | 22.83 |