TY - JOUR T1 - Self-supervised pre-training of CNNs for flatness defect classification in the steelworks industry JF - International Journal of Advances in Intelligent Informatics Y1 - 2020 A1 - Filippo Galli A1 - Antonio Ritacco A1 - Giacomo Lanciano A1 - Marco Vannocci A1 - Valentina Colla A1 - Marco Vannucci KW - CNN KW - Deep learning KW - Self-supervision KW - Steelworks AB - Classification of surface defects in the steelworks industry plays a significant role in guaranteeing the quality of the products. From an industrial point of view, a serious concern is represented by the hot-rolled products shape defects and particularly those concerning the strip flatness. Flatness defects are typically divided into four sub-classes depending on which part of the strip is affected and the corresponding shape. In the context of this research, the primary objective is evaluating the improvements of exploiting the self-supervised learning paradigm for defects classification, taking advantage of unlabelled, real, steel strip flatness maps. Different pre-training methods are compared, as well as architectures, taking advantage of well-established neural subnetworks, such as Residual and Inception modules. A systematic approach in evaluating the different performances guarantees a formal verification of the self-supervised pre-training paradigms evaluated hereafter. In particular, pre-training neural networks with the EgoMotion meta-algorithm shows classification improvements over the AutoEncoder technique, which in turn is better performing than a Glorot weight initialization. VL - 6 UR - http://ijain.org/index.php/IJAIN/article/view/410 ER -