Active Vision for Deep Visual Learning: A Unified Pooling Framework

Convolutional neural networks (CNNs) can be generally regarded as learning-based visual systems for computer vision tasks. By imitating the operating mechanism of the human visual system (HVS), CNNs can even achieve better results than human beings in some visual tasks. However, they are primary when compared to the HVS for the reason that the HVS has the ability of active vision to promptly analyze and adapt to specific tasks. In this article, a new unified pooling framework is proposed and a series of pooling methods are designed based on the framework to implement active vision to CNNs. In addition, an active selection pooling (ASP) is put forward to reorganize the existing and newly proposed pooling methods. The CNN models with an ASP tend to have a behavior of focus selection according to tasks during the training process, which acts extremely similar to the HVS.