WRGPruner: A new model pruning solution for tiny salient object detection

Fengwei Jia, Xuan Wang, Jian Guan, Huale Li, Chen Qiu, Shuhan Qi

Abstract: Highlights•Define the new concept salient energy level (SEL) to assess the parameters' ability to distinguish importance.•Propose the novel method WRGPruner that simultaneously consider the synthesis of three dimensions.•Mathematically prove the effectiveness of the WRGPruner for tiny salient object detection.•Construct a tiny salient object dataset (TSOD) and its extension version TSOD-S, TSOD-M, and TSOD-L.