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
- EP ID EP409155
- DOI 10.26480/iscsai.01.2017.33.35
- Views 87
- Downloads 0
RESEARCH AND APPLICATION OF INTEGRAL SEPARATION PID CONTROL BASED ON FUZZY CONTROL IN INTELLIGENT CAR
The wheel-type robot has a high degree of nonlinearity in the process of intelligent tracking control in a closed-loop environment. The speed and direction of the wheel-type robot need real-time control both in the strai...
AN ANALYSIS ON DIAGNOSTIC METHOD OF ROLLER BEARING FAULTS BASED ON AUDITORY SPECTRUM AND SPECTRAL CORRELATION
Human auditory system possesses a desirable capacity for analyzing, processing and identifying signals. Whereas different types of rolling bearing faults cause different vibration noises, a new method based on early audi...
AN IMPROVED HYBRID RECOMMENDATION ALGORITHM STUDY AND DESIGN ON MAHOUT FRAMEWORK
Collaborative filtering algorithm is one of the most widely used algorithms in the recommendation system. However, each collaborative filtering algorithm has its advantages and disadvantages. When applied to recommendati...
COMPLICATED MECHANICAL EQUIPMENT DIAGNOSIS BASED ON BAYESIAN NETWORKS
Mechanical equipment fault diagnosis is a complicated process. Due to the complex structure, the different operating environment, the different detection means and testing equipment, the difference between the operator a...
DESIGN TEMPERATURE AND LIQUID LEVEL CONTROL SYSTEM
Along long to the continuance is developing of science and technologies for this level to is people’s daily is lives keeping improved, so many smart devices location appear on people’s daily lives, and this temperature i...