DCoM: Active Learning for All Learners

TL;DR

DCoM is a novel active learning method that adaptively adjusts its strategy based on model competence, effectively reducing annotation costs across various budget scenarios in deep learning tasks.

Contribution

Introduces DCoM, a dynamic active learning approach that adjusts strategies based on model competence, improving performance across low- and high-budget regimes.

Findings

DCoM outperforms existing methods in diverse datasets.

It overcomes the cold start problem effectively.

Achieves state-of-the-art results across budget scenarios.

Abstract

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.