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.