Active learning using weakly supervised signals for quality inspection

TL;DR

This paper presents an active learning approach that leverages weakly supervised signals and domain-adversarial training to improve machine vision quality inspection systems amid evolving manufacturing conditions and limited annotations.

Contribution

It introduces a methodology for learning from rapidly mined, weakly annotated data and addresses covariate shift with domain-adversarial training, enabling faster and more adaptable inspection systems.

Findings

Effective prioritization of annotation process

Reduction in false positives in inspection

Improved robustness to changing data conditions

Abstract

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.