PlantBiCNet: A new paradigm in plant science with bi-directional cascade neural network for detection and counting

Jianxiong Ye, Zhenghong Yu, Yangxu Wang, Dunlu Lu, Huabing Zhou

Abstract: Highlights•Reorganized and shared six challenging plant detection and counting datasets on GitHub.•Proposed two new paradigms, achieving state-of-the-art performance.•Provided a network modeling approach for resource-limited plant science.•Validated the effectiveness of Dropout strategy in plants science.