For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Parallel Feature Network For Saliency Detection
Zheng FANG Tieyong CAO Jibin YANG Meng SUN
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2019/02/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
saliency detection, convolution neural network, parallel feature network, parallel dilation block, feature upsample and fusion,
Full Text: PDF(3.5MB)>>
Saliency detection is widely used in many vision tasks like image retrieval, compression and person re-identification. The deep-learning methods have got great results but most of them focused more on the performance ignored the efficiency of models, which were hard to transplant into other applications. So how to design a efficient model has became the main problem. In this letter, we propose parallel feature network, a saliency model which is built on convolution neural network (CNN) by a parallel method. Parallel dilation blocks are first used to extract features from different layers of CNN, then a parallel upsampling structure is adopted to upsample feature maps. Finally saliency maps are obtained by fusing summations and concatenations of feature maps. Our final model built on VGG-16 is much smaller and faster than existing saliency models and also achieves state-of-the-art performance.