SOURCE-LINKED INTELLIGENCE

ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, either relying on expensive dataset-specific policy search or applying transformations uniformly at random, regardless of what the model has already learned. We introduce ActiveAugment, a unified framework that treats augmentation selection as an online active learning problem. For each training minibatch, ActiveAugment generates a pool of candidate augmented views and scores each candidate using a combination of the model's predictive uncertainty and

Read original source ↗ Open in workspace

recordType

paper

region

Global