OSA-PD: Open-Set Active Learning Exploiting Predictive Discrepancy

Active learning with closed-set annotation has achieved significant success. However, real-world data often comprises numerous unknown classes irrelevant to the task which often confuses the query strategies to select unknown class data for annotation. To address such challenge in the open-set annotation (OSA), we propose a novel open-set active learning framework based on predictive discrepancy, named OSA-PD, with consideration that valuable data for model improvement is often with high predictive discrepancy. Specifically, two algorithms based on different discrepancy measurements are presented under OSA-PD framework, i.e., OSA-PRD with predictive results discrepancy, and OSA-PDD with decoupled predictive distribution discrepancy. Experimental results on CIFAR100 and TinyImageNet demonstrate the proposed OSA-PD can effectively select known class data and achieve higher classification accuracy with the same amount of annotated sample in comparison with existing active learning algorithms.