FSRFNet: Feature-selective and Spatial Receptive Fields Networks

Abstract

The attention mechanism plays a crucial role in the human visual experience. In the cognitive neuroscience community, the receptive field size of visual cortical neurons is regulated by the additive effect of feature-selective and spatial attention. We propose a novel architectural unit called a “Feature-selective and Spatial Receptive Fields” (FSRF) block that implements adaptive receptive field sizes of neurons through the additive effects of feature-selective and spatial attention. We show that FSRF blocks can be inserted into the architecture of existing convolutional neural networks to form an FSRF network architecture, and test its generalization capabilities on different datasets.

Keywords

• attention mechanism
• additive effect
• feature-selective and spatial attention
• convolutional neural network