Weakly Supervised Few-Shot Segmentation Via Meta-Learning
This work addresses data scarcity in semantic segmentation for medical and agricultural applications, offering a weakly supervised approach that reduces labeling effort, though it appears incremental as it builds on existing meta-learning and few-shot techniques.
The paper tackles the problem of laborious pixel-level labeling for semantic segmentation by proposing two meta-learning methods, WeaSeL and ProtoSeg, for few-shot segmentation with sparse annotations. The methods achieved suitable results for segmenting coffee/orange crops and anatomical body parts across 12 datasets in medical imaging and agricultural remote sensing.
Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances with deep-based approaches, labeling samples (pixels) for training models is laborious and, in some cases, unfeasible. In this paper, we present two novel meta learning methods, named WeaSeL and ProtoSeg, for the few-shot semantic segmentation task with sparse annotations. We conducted extensive evaluation of the proposed methods in different applications (12 datasets) in medical imaging and agricultural remote sensing, which are very distinct fields of knowledge and usually subject to data scarcity. The results demonstrated the potential of our method, achieving suitable results for segmenting both coffee/orange crops and anatomical parts of the human body in comparison with full dense annotation.