Search

This article proposes an unsupervised method for learning compositional sparse code for representing natural images. Our method is built upon the original sparse coding framework where there is a dictionary of basis functions often in the form of localized, elongated and oriented wavelets, so that each image can be represented by a linear combination of a small number of basis functions automatically selected from the dictionary. In our compositional sparse code, the representational units are composite: they are compositional patterns formed by the basis functions. These compositional patterns can be viewed as shape templates. We propose an unsupervised learning method for learning a dictionary of frequently occurring templates from training images, so that each training image can be represented by a small number of templates automatically selected from the learned dictionary. The compositional sparse code approximates the raw image of a large number of pixel intensities using a small number of templates, thus facilitating the signal-to-symbol transition and allowing a symbolic description of the image. The current form of our model consists of two layers of representational units (basis functions and shape templates). It is possible to extend it to multiple layers of hierarchy. Experiments show that our method is capable of learning meaningful compositional sparse code, and the learned templates are useful for image classification. [ABSTRACT FROM AUTHOR]

EM algorithm is a convenient tool for maximum likelihood model fitting when the data are incomplete or when there are latent variables or hidden states. In this review article we explain that EM algorithm is a natural computational scheme for learning image templates of object categories where the learning is not fully supervised. We represent an image template by an active basis model, which is a linear composition of a selected set of localized, elongated and oriented wavelet elements that are allowed to slightly perturb their locations and orientations to account for the deformations of object shapes. The model can be easily learned when the objects in the training images are of the same pose, and appear at the same location and scale. This is often called supervised learning. In the situation where the objects may appear at different unknown locations, orientations and scales in the training images, we have to incorporate the unknown locations, orientations and scales as latent variables into the image generation process, and learn the template by EM-type algorithms. The E-step imputes the unknown locations, orientations and scales based on the currently learned template. This step can be considered self-supervision, which involves using the current template to recognize the objects in the training images. The M-step then relearns the template based on the imputed locations, orientations and scales, and this is essentially the same as supervised learning. So the EM learning process iterates between recognition and supervised learning. We illustrate this scheme by several experiments. [ABSTRACT FROM AUTHOR]