Object localization via evaluation multi-task learning

doi:10.1016/j.neucom.2017.01.098

Object localization via evaluation multi-task learning

2017-08-01

19

PRE

AI

DOI：10.1016/j.neucom.2017.01.098

原文链接

原文求助

摘要

En 中文

Research on Region Convolution Neural Network (RCNN) based object localization has recently witnessed rapid progress, but constrained by the size of the output convolution map, this method is unable to obtain exact object positions. In this paper, we present a multi-task learning approach on convolution neural network for object localization. Our model consists of 3 modules, respectively extracting shared features, generating low-level features, and fusing different levels information. We developed an algorithm for the nontrivial end-to-end training of this causal, cascaded structure. Finally, we demonstrated performance of the algorithm on the PASCAL VOC 2007 dataset and traffic scene dataset. Experiments show that our algorithm effectively and efficiently improved performance. (C) 2017 Elsevier B.V. All rights reserved.

Keyword:

Object localization

Edge information

Multi-task network

Deep learning

Information fusion

Object localization via evaluation multi-task learning

摘要

AI总结

期刊

机构

引用论文