The recognition of partially occluded objects with support vector machines, convolutional neural networks and deep belief networks

Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images.