Robust Adversarial Active Learning with a Novel Diversity Constraint

Active learning adopts an iterative process that prioritizes the labeling of the most informative samples. However, in many real-world applications, the training data usually contains Out-of-Distribution (OoD) samples that affect the robustness of the trained models. Unfortunately, most existing active learning approaches focus on the uncertainty measure, thus have a bias towards selecting OoD samples. In this paper, we propose a robust adversarial active learning method that performs well on datasets with OoD samples. First, we incorporate recent advances in adversarial networks into an active learning framework to select the samples that are most dissimilar to the labeled pool. Secondly, we design a novel loss function based on Earth-Mover (EM) distance, which makes the model training more stable. Moreover, we propose a novel diversity constraint learned from feature space that penalizes the OoD samples. Experimental evaluation results on the datasets of varying size demonstrate the effectiveness of our approach.