SALIENCY DETECTION VIA DENSE CONVOLUTION NETWORK

Journal Title: Topics in Intelligent Computing and Industry Design (ICID) - Year 2017, Vol 1, Issue 3

Abstract

Saliency detection is a fundamental problem in the field of image processing and computer vision. The convolutional model has been also used in saliency detection for its outstanding performance on image classification and localization task. In this paper, we propose a novel way to detect the salient object by modifying the Dense Convolution Network (DenseNet). We replace the fully-connected layer and the final pooling layer in DenseNet into a convolution layer and a deconvolution layer to fit the saliency detection task. And our network ends up with a squared Euclidean loss layer for saliency regression. Our network is end-to-end architecture which outputs saliency maps directly. Experimental results demonstrate that our approach is competitive in comparison with the state-of-the-art approaches.

Authors and Affiliations

Zheng Fang, Tieyong Cao, Yibo Xing

Keywords

Related Articles

STUDY OF LEGAL ISSUES IN SHARING BIKE OPERATION

By the end of 2016, sharing bike was born in China as a low-carbon environmental protection way to effectively solve the trip of the “last mile” problem, which is an emerging thing during the development of socialism in...

RESEARCH ON THE INFLUENCE FACTORS OF THE DROPLETS VOLUME OF JETTING DISPENSER

The droplets volume is an important indicator to evaluate the quality of dispensing, and there are many factors that affect the volume of droplets, such as the liquid viscosity, the fluid cavity temperature, the driving...

APPLICATION OF COMPUTER TECHNOLOGY IN HEMODIALYSIS MANAGEMENT SYSTEM

In recent years, the number of patients with kidney disease in China has increased rapidly, and the number and size of hemodialysis centers have increased. At present, the hemodialysis work is facing more patients, equip...

BAND GAP CHARACTERISTICS OF ONE-DIMENSIONAL QUASI-PERIODIC PHONONIC CRYSTALS WITH LAYER THICKNESS ARRANGED BY TM (THUE MORSE) SEQUENCE

In order to decrease the band gap frequency, a model of one dimensional quasi-periodic phononic crystals with layer thickness arranged by TM sequence was proposed. Its band structure was investigated numerically using th...

PREPARATION AND PERFORMANCE OF MICROORGANISM MINERALIZED STEEL SLAG CEMENTING MATERIAL

In this paper, the steel slag-lime system was used to prepare steel slag products under the enzymatic action of microorganisms. The results showed that, after 3h carbonization, the compressive strength increased from 32....

Download PDF file
  • EP ID EP409155
  • DOI 10.26480/iscsai.01.2017.33.35
  • Views 60
  • Downloads 0

How To Cite

Zheng Fang, Tieyong Cao, Yibo Xing (2017). SALIENCY DETECTION VIA DENSE CONVOLUTION NETWORK. Topics in Intelligent Computing and Industry Design (ICID), 1(3), 33-35. https://europub.co.uk./articles/-A-409155