基于弱监督学习的去噪受限玻尔兹曼机特征提取算法

针对现有特征提取方法难以实现从含有复杂背景的图像中提取有用目标特征的瓶颈问题,提出了基于弱监督学习的去噪受限玻尔兹曼机特征提取算法.首先,利用训练样本,通过无监督学习方式训练一个标准受限玻尔兹曼机模型,从而获得一个包含可视单元层和隐藏单元层的层次结构模型;然后,对可视层的每个单元引入二值转换单元,对隐藏层,根据各节点的激活值大小和激活频率将其分为两组:前景特征隐层单元和背景特征隐层单元,得到一个二元混合式去噪玻尔兹曼机的模型;最后,通过多模交互方式,利用有限数量的样本标签信息对输入样本逐像素地进行采样训练,以此来提取目标特征.实验表明,本文的特征提取算法能够有效地从复杂的干扰背景中提取目标特征,提高了目标识别精度.

Weakly Supervised Learning with Denoising Restricted Boltz mann Machines for Extracting Featu res

Existing feature extraction algorithms are difficult to capture useful information from complex images.A feature extraction approach is proposed based on the weakly supervised learning with denoising restricted Boltzmann machine(RBM).First,a standard RBM is pre-trained in an unsupervised learning way,which provides a hierarchical mode with a visible layer and a hidden layer.Second,for the visible layer,a stochastic binary switch node is employed.And for the hidden layer,it is divided into foreground-hidden nodes and background-hidden nodes based on the score of each hidden node's activation values and times,thus we can achieve a binary mixture denoising RBMs.Finally,the pixel-wise denoising RBMs is trained by using small number label information and stochastic switch nodes through multiplicative interaction.The experimental results show that significant performance improvement is achieved with our proposed method.