Designing Synthetic Active Learning for model refinement in manufacturing parts detection

This paper introduces Synthetic Active Learning (SAL), a fully automatic model refinement strategy for manufacturing parts detection using only synthetic data actively generated with domain randomization for training. SAL iteratively updates the detection model by identifying its weaknesses, such as in specific categories, materials, or object sizes, using custom evaluators, and generating targeted synthetic data to address them; it selectively synthesizes new useful data with respect to active learning, where traditionally humans in the loop select data to label. During each iteration, model training and data generation occur simultaneously to improve efficiency. Evaluated on four use cases from two industrial datasets, SAL achieved mAP@50 improvements of 2 to 6% percentage points over static learning, which refers to training on a fixed, pre-generated dataset. It also showed notable gains in underperforming categories, leading to more balanced performance across classes. Another benefit is that it uses a consistent configuration across multiple use cases, avoiding the need for extensive hyperparameter tuning common in prior domain randomization studies. Given its encouraging performance across diverse scenarios, we believe that SAL can scale to broader industrial applications where training can be fully or mostly based on synthetic data.