AFINet: Attentive Feature Integration Networks for Image Classification
AFINet: Attentive Feature Integration Networks for Image Classification
Xinglin Pan,Jing Xu,4 Authors,Zenglin Xu
2021 · DOI: 10.1016/j.neunet.2022.08.026
Neural Networks · 10 Citations
TLDR
Attentive Feature Integration (AFI) modules are designed, which are widely applicable to most residual-like network architectures, leading to new architectures named AFI-Nets, which obtains a 1.24% relative improvement on the ImageNet dataset while decreases the FLOPs and the number of parameters compared to ResNet-152.