Weakly Supervised Fruit Counting for Yield Estimation using Spatial Consistency

Fruit counting is a fundamental component for yield estimation.Most of the SotA approaches address the problem using fruit models or by explicitly learning to count. In this paper, we tackle the problem by proposing a framework that learns to count fruits without the need for task-specific supervision labels. The experiments on different varieties of fruits show that our approach reaches performances that are comparable with SotA approaches based on the supervised paradigm.