Visual Perceptual Learning

Perceptual learning should be considered as an active process that embeds particular abstraction, reformulation and approximation within the Abstraction framework. The active process refers to the fact that the search for a correct data representation is performed through several steps. A key point is that perceptual learning focuses on low-level abstraction mechanism instead of trying to rely on more complex algorithm. In fact, from the machine learning viewpoint, Perceptual learning can be seen as a particular abstraction that may help to simplify complex problem thanks to a computable representation. Indeed, the baseline of Abstraction, i.e. choosing the relevant data to ease the learning task, is that many problems in machine learning cannot be solve because of the complexity of the representation and is not related to the learning algorithm, which is referred to as the phase transition problem. Within the Abstraction framework, we use the term perceptual learning to refer to specific learning task that rely on iterative representation changes and that deals with real-world data which human can perceive. In this talk we focus on sparse coding theory and granular computing model for visual perceptual learning. We propose an attention-guided sparse coding model. This model includes two modules: nonuniform sampling module simulating the process of retina and data-driven attention module based on the response saliency. Based on tolerance relation we construct a more uniform granulation model, which is established on both consecutive space and discrete attribute space.