Deep and Structured Robust Information Theoretic Learning for Image Analysis
Deep and Structured Robust Information Theoretic Learning for Image Analysis
复制标题
用于图像分析的深度结构化鲁棒信息理论学习
DOI：
10.1109/tip.2016.2588330
复制
发表时间：
2016-09-01
影响因子：
10.6
通讯作者：
Dai, Qionghai
中科院分区：
文献类型：
--
作者：
Deng, Yue;Bao, Feng;Dai, Qionghai
This paper presents a robust information theoretic (RIT) model to reduce the uncertainties, i.e., missing and noisy labels, in general discriminative data representation tasks. The fundamental pursuit of our model is to simultaneously learn a transformation function and a discriminative classifier that maximize the mutual information of data and their labels in the latent space. In this general paradigm, we, respectively, discuss three types of the RIT implementations with linear subspace embedding, deep transformation, and structured sparse learning. In practice, the RIT and deep RIT are exploited to solve the image categorization task whose performances will be verified on various benchmark data sets. The structured sparse RIT is further applied to a medical image analysis task for brain magnetic resonance image segmentation that allows group-level feature selections on the brain tissues.
