Active Pointly-Supervised Instance Segmentation
This addresses the annotation burden for researchers and practitioners in computer vision, though it is incremental as it builds on existing active learning and point-based supervision methods.
The paper tackles the problem of expensive annotation costs in instance segmentation by introducing an active learning setting called APIS, which uses box-level annotations and iteratively samples points to query, achieving consistent performance gains on MS-COCO with limited budgets.
The requirement of expensive annotations is a major burden for training a well-performed instance segmentation model. In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The key of APIS is to find the most desirable points to maximize the segmentation accuracy with limited annotation budgets. We formulate this setting and propose several uncertainty-based sampling strategies. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset, compared against other learning strategies. The results suggest that APIS, integrating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentation.