Active learning using weakly supervised signals for quality inspection
This work addresses the problem of costly and slow annotation for quality inspection in manufacturing, offering an incremental improvement to existing active learning methods.
The paper tackles the challenge of rapidly updating machine vision inspection systems in manufacturing by developing an active learning methodology that uses weakly annotated data to prioritize and accelerate annotation, reducing false positives and addressing covariate shift with domain-adversarial training.
Because manufacturing processes evolve fast, and since production visual aspect can vary significantly on a daily basis, the ability to rapidly update machine vision based inspection systems is paramount. Unfortunately, supervised learning of convolutional neural networks requires a significant amount of annotated images for being able to learn effectively from new data. Acknowledging the abundance of continuously generated images coming from the production line and the cost of their annotation, we demonstrate it is possible to prioritize and accelerate the annotation process. In this work, we develop a methodology for learning actively, from rapidly mined, weakly (i.e. partially) annotated data, enabling a fast, direct feedback from the operators on the production line and tackling a big machine vision weakness: false positives. We also consider the problem of covariate shift, which arises inevitably due to changing conditions during data acquisition. In that regard, we show domain-adversarial training to be an efficient way to address this issue.