Parallel Feature Network For Saliency Detection

Zheng FANG  Tieyong CAO  Jibin YANG  Meng SUN  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E102-A   No.2   pp.480-485
Publication Date: 2019/02/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E102.A.480
Type of Manuscript: LETTER
Category: Image
saliency detection,  convolution neural network,  parallel feature network,  parallel dilation block,  feature upsample and fusion,  

Full Text: PDF(3.5MB)>>
Buy this Article

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.