Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in more volatile scenarios, such as remanufacturing, where the inspected products and defect patterns often change. In such settings, deployed models require frequent adaptation to novel conditions, effectively posing a continual learning problem. To enable quick adaptation, the necessary training processes must be computationally efficient while still avoiding effects like catastrophic forgetting. This work presents a multi-level feature fusion (MLFF) approach that aims to improve both aspects simultaneously by utilizing representations from different depths of a pretrained network. We show that our approach is able to match the performance of end-to-end training for different quality inspection problems while using significantly less trainable parameters. Furthermore, it reduces catastrophic forgetting and improves generalization robustness to new product types or defects.

翻译：深度神经网络在自动化制造业中各类视觉质量检测任务方面展现出巨大潜力。然而，其在更易变场景（如再制造）中的适用性有限，因为此类场景中待检产品和缺陷模式常发生变化。在此类场景下，已部署模型需要频繁适应新条件，这实质上构成了持续学习问题。为实现快速适应，必要的训练过程必须在保持计算高效性的同时，避免灾难性遗忘等效应。本研究提出一种多级特征融合方法，该方法通过利用预训练网络不同深度的表征，旨在同时改善这两个方面。我们证明，该方法能够在显著减少可训练参数的同时，在不同质量检测问题上达到端到端训练的性能水平。此外，该方法能减轻灾难性遗忘现象，并提升对新产品类型或缺陷的泛化鲁棒性。