AFINet: Attentive Feature Integration Networks for image classification. (November 2022)

• Record Type: Journal Article
• Authors: Pan, Xinglin; Xu, Jing; Pan, Yu; Wen, Liangjian; Lin, Wenxiang; Bai, Kun; Fu, Hongguang; Xu, Zenglin
• Is Part Of: Neural networks. Volume 155(2022)
• Page Start: 360
• Page End: 368
• Publication Date: 2022-11
• Subjects: CNN -- Attention -- Image classification -- Feature integration; 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.2022.08.026
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Residual-like networks, such as ResNets, mainly focus on the skip connection to avoid gradient vanishing. However, the skip connection mechanism limits the utilization of intermediate features due to simple iterative updates. To mitigate the redundancy of residual-like networks, we design Attentive Feature Integration (AFI) modules, which are widely applicable to most residual-like network architectures, leading to new architectures named AFI-Nets. AFI-Nets explicitly model the correlations among different levels of features and selectively transfer features with a little overhead. AFI-ResNet-152 obtains a 1.24% relative improvement on the ImageNet dataset while decreases the FLOPs by about 10% and the number of parameters by about 9.2% compared to ResNet-152.