Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
This work tackles the problem of high annotation costs in instance segmentation, particularly relevant for domains like medical imaging where expert labeling is expensive and time-consuming.
This paper addresses the high annotation cost of instance segmentation by proposing a semi-supervised active learning framework. The method, Triplet Scoring Predictions (TSP), effectively leverages both labeled and unlabeled data to achieve state-of-the-art performance with significantly reduced annotation costs on medical image datasets.
Active learning generally involves querying the most representative samples for human labeling, which has been widely studied in many fields such as image classification and object detection. However, its potential has not been explored in the more complex instance segmentation task that usually has relatively higher annotation cost. In this paper, we propose a novel and principled semi-supervised active learning framework for instance segmentation. Specifically, we present an uncertainty sampling strategy named Triplet Scoring Predictions (TSP) to explicitly incorporate samples ranking clues from classes, bounding boxes and masks. Moreover, we devise a progressive pseudo labeling regime using the above TSP in semi-supervised manner, it can leverage both the labeled and unlabeled data to minimize labeling effort while maximize performance of instance segmentation. Results on medical images datasets demonstrate that the proposed method results in the embodiment of knowledge from available data in a meaningful way. The extensive quantitatively and qualitatively experiments show that, our method can yield the best-performing model with notable less annotation costs, compared with state-of-the-arts.