scholarly journals Structural Learning of Activities from Sparse Datasets

2007 ◽  
Author(s):  
Fahd Albinali ◽  
Nigel Davies ◽  
Adrian Friday
Keyword(s):  
Structural Learning

scholarly journals Mixed states on neural network with structural learning

2004 ◽  
Vol 17 (1) ◽  
pp. 103-112 ◽  
Author(s):  
Tomoyuki Kimoto ◽  
Masato Okada
Keyword(s):  
Neural Network ◽  
Structural Learning ◽  
Mixed States

Structural learning of Bayesian networks using local algorithms based on the space of orderings

2010 ◽  
Vol 15 (10) ◽  
pp. 1881-1895 ◽  
Author(s):  
Juan I. Alonso-Barba ◽  
Luis delaOssa ◽  
Jose M. Puerta
Keyword(s):  
Bayesian Networks ◽  
Structural Learning ◽  
Local Algorithms

scholarly journals Adversarial Deep Structural Networks for Mammographic Mass Segmentation

2016 ◽  
Author(s):  
Wentao Zhu ◽  
Xiaohui Xie
Keyword(s):  
Conditional Random Fields ◽  
Model Potential ◽  
Natural Image ◽  
Structural Learning ◽  
Mass Detection ◽  
Convolutional Network ◽  
Adversarial Training ◽  
Mass Segmentation ◽  
End To End ◽  
Public Datasets

AbstractMass segmentation is an important task in mammogram analysis, providing effective morphological features and regions of interest (ROI) for mass detection and classification. Inspired by the success of using deep convolutional features for natural image analysis and conditional random fields (CRF) for structural learning, we propose an end-to-end network for mammographic mass segmentation. The network employs a fully convolutional network (FCN) to model potential function, followed by a CRF to perform structural learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with position priori for the task. Due to the small size of mammogram datasets, we use adversarial training to control over-fitting. Four models with different convolutional kernels are further fused to improve the segmentation results. Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.

Sign in / Sign up

Export Citation Format

Share Document