Deep Active Learning for Computer Vision: Past and Future

As an important data selection schema, active learning emerges as the essential component when iterating Artificial Intelligence (AI) model. It becomes even more critical given dominance of deep neural network based models, which are composed a large number parameters and hungry, in application. Despite its indispensable role for developing AI research on is not intensive other directions. In this paper, we present review through approaches from following perspectives: 1) technical advancements learning, 2) applications computer vision, 3) industrial systems leveraging or with potential to leverage iteration, 4) current limitations future We expect paper clarify significance modern model manufacturing process bring additional attention learning. By addressing automation challenges coping automated machine systems, will facilitate democratization technologies by boosting production at scale.