Contrastive Learning with Sparsely Annotated Dataset for Apple Detection in Smart Orchard Farming

Detecting and locating apples is important for picking robots and orchard management. Although fully-supervised object detection (FSOD) methods have achieved impressive apple detection performance, the required annotated large-scale datasets are expensive. To balance the annotation cost and detection performance, a contrastive learning based apple detection method with sparsely annotated dataset (CLAD-SAD) is proposed, in which a Similarity-based Group Pseudo Label Generating (SGPLG) module is exploited to take advantage of unlabeled instances by generating pseudo labels based on the similarity between existing instances and unlabeled regions. Furthermore, a contrastive learning loss function within the heatmap prediction branch is used to improve the tolerance of false pseudo labels. In addition, Aspect Ratio Filtering Module (ARFM) is added to filter out the low-quality prediction boxes with imbalanced aspect ratios. By this, the proposed CLAD-SAD markedly improve the apple detection performance with limited annotated dataset. Experimental results show that our proposed method improves mAP and mAR by 6.7% and 3.7%, respectively, on sparsely annotated datasets compared to the traditional FSOD model. This indicates that the proposed ARFM is feasible to apple detection with limited annotated dataset, which addressing the challenge of traditional models’ reliance on large-scale annotated datasets.