361 0

Adaptive Region Pooling for Object Detection

Title
Adaptive Region Pooling for Object Detection
Author
Yang, Ming-hsuan
Keywords
Feature extraction; Proposals; Training; Adaptation models; Testing; Object detection; Image segmentation
Issue Date
2015-06
Publisher
IEEE
Citation
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 731-739
Abstract
Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.
URI
http://ieeexplore.ieee.org/document/7298673/?isnumber=7298593&arnumber=7298673http://hdl.handle.net/20.500.11754/25639
ISBN
978-1-4673-6964-0
ISSN
1063-6919
DOI
10.1109/CVPR.2015.7298673
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE