Spatial Bias for attention-free non-local neural networks

Junhyung Go, Jongbin Ryu

Abstract: Highlights•We introduce Spatial Bias, a lightweight non-local method in neural networks.•The proposed method learns long-range dependencies with a convolution layer.•The proposed Spatial Bias is fairly quick and show competitive performance.•The proposed Spatial Bias can be used with the existing non-local methods.