DCoM: Active Learning for All Learners
This addresses the problem of reducing annotation costs for deep models in computer vision, though it appears incremental as it builds on existing active learning techniques.
The paper tackles the challenge of active learning effectiveness across varying budget scenarios by introducing DCoM, a dynamic approach that adjusts strategy based on model competence, achieving state-of-the-art performance in both low- and high-budget regimes.
Deep Active Learning (AL) techniques can be effective in reducing annotation costs for training deep models. However, their effectiveness in low- and high-budget scenarios seems to require different strategies, and achieving optimal results across varying budget scenarios remains a challenge. In this study, we introduce Dynamic Coverage & Margin mix (DCoM), a novel active learning approach designed to bridge this gap. Unlike existing strategies, DCoM dynamically adjusts its strategy, considering the competence of the current model. Through theoretical analysis and empirical evaluations on diverse datasets, including challenging computer vision tasks, we demonstrate DCoM's ability to overcome the cold start problem and consistently improve results across different budgetary constraints. Thus DCoM achieves state-of-the-art performance in both low- and high-budget regimes.