Visual interaction networks: A novel bio-inspired computational model for image classification. (October 2020)

• Record Type: Journal Article
• Authors: Wei, Bing; He, Haibo; Hao, Kuangrong; Gao, Lei; Tang, Xue-song
• Is Part Of: Neural networks. Volume 130(2020)
• Page Start: 100
• Page End: 110
• Publication Date: 2020-10
• Subjects: Biologically inspired computing -- Convolutional neural network (CNN) -- Visual interaction mechanism -- Textile defect -- Image classification; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2020.06.019
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Inspired by biological mechanisms and structures in neuroscience, many biologically inspired visual computational models have been presented to provide new solutions for visual recognition task. For example, convolutional neural network (CNN) was proposed according to the hierarchical structure of biological vision, which could achieve superior performance in large-scale image classification. In this paper, we propose a new framework called visual interaction networks (VIN-Net), which is inspired by visual interaction mechanisms. More specifically, self-interaction, mutual-interaction, multi-interaction, and adaptive interaction are proposed in VIN-Net, forming the first interactive completeness of the visual interaction model. To further enhance the representation ability of visual features, the adaptive adjustment mechanism is integrated into the VIN-Net model. Finally, our model is evaluated on three benchmark datasets and two self-built textile defect datasets. The experimental results demonstrate that the proposed model exhibits its efficiency on visual classification tasks. Furthermore, a textile industrial application shows that the proposed architecture outperforms the state-of-the-art approaches in classification performance.