Weakly Supervised Few-Shot Segmentation Via Meta-Learning

• DOI: 10.48550/arxiv.2109.01693
• Publication Date: 2021-01-01
• Authors: Pedro H. T. Gama; Hugo Gonçalo Oliv...; José Marcato Junior; Jefersson A. dos ...
• Keywords: Market Segmentation; Labeled data

Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances deep-based approaches, labeling samples (pixels) for training models laborious and, in some cases, unfeasible. In this paper, we present two novel meta learning methods, named WeaSeL ProtoSeg, the few-shot semantic sparse annotations. We conducted extensive evaluation of proposed methods different applications (12 datasets) imaging agricultural sensing, are very distinct fields knowledge usually subject to data scarcity. The results demonstrated potential our method, achieving suitable segmenting both coffee/orange crops anatomical parts human body comparison full dense annotation.