An Industrial Application of Semi-supervised techniques for automatic surface inspection of stainless steel. : Are pseudo-labeling and consistency regularization effective in a real industrial context?

Abstract: Recent developments in the field of Semi-Supervised Learning are working to avoid the bottleneck of data labeling. This can be achieved by leveraging unlabeled data to limit the amount of labeled data needed for training deep learning models. Semi-supervised learning algorithms are showing promising results; however, research has been focusing on algorithm development, without proceeding to test their effectiveness in real-world applications. This research project has adapted and tested some semi-supervised learning algorithms on a dataset extracted from the manufacturing en-vironment, in the context of the surface analysis of stainless steel, in collaboration with Outokumpu Stainless Oy. In particular, a simple algorithm combining Pseudo-Labeling and Consistency Regularization has been developed, inspired by the state-of-the-art algorithm Fix match. The results show some potential, because the usage of Semi-Supervised Learning techniques has significantly reduced overfitting on the training set, while maintaining a good accuracy on the test set. However, some doubts are raised regarding the application of these techniques in a real environment, due to the imperfect nature of real datasets and the high algorithm development cost due to the increased complexity introduced with these methods.