2020/12/09 by Jun Wang, Shaoguo Wen, Wang, Jun +13
Computer Science · #Annotation #Artificial intelligence #Bounding overwatch #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Labeled data #Leverage (statistics) #Machine Learning and Algorithms #Machine Learning and Data Classification #Machine learning #Pattern recognition (psychology) #Ranking (information retrieval) #Segmentation #Semi-supervised learning #Task (project management) #cs.CV #cs.HC
paper · pdf · doi:10.48550/arxiv.2012.04829
13 pages, 7 figures, accepted for presentation at BMVC2020
arxiv created 2020/12/09 · openalex publication_date 2020/12/09 · arxiv updated 2020/12/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.