FP-Nets for Blind Image Quality Assessment

Feature-Product networks (FP-nets) are a novel deep-network architecture inspired by principles of biological vision. These contain the so-called FP-blocks that learn two different filters for each input feature map, outputs which then multiplied. Such an is models end-stopped neurons, common in cortical areas V1 and especially V2. The authors here use FP-nets on three image quality assessment (IQA) benchmarks blind IQA. They show using FP-nets, they can obtain deliver state-of-the-art performance while being significantly more compact than competing models. A further improvement due to simple attention mechanism. good results report may be related fact employ bio-inspired design principles.