*Result*: Towards label-free defect detection in additive manufacturing via dual-classifier semi-supervised learning for vision-language models.

*Complex components can now be fabricated in innovative ways thanks to additive manufacturing (AM) technology, but it also presents a severe challenge in the detection of defects, primarily due to extensive labeling efforts of defect samples. In order to address the labeling problem in AM defect identification, this work suggests a unique strategy called the Dual-Classifier Semi-supervised Learning (DCSL) method. DCSL reduces the requirement for intensive tagging and improves detection accuracy by utilizing both labeled and unlabeled data. Two distinct classifiers, namely the one-hot classifier and the semantic classifier, are designed to train the defect class labels from different perspectives. The one-hot classifier adopts a one-hot encoding of labels, treating each class independently from the visual perspective, while the semantic classifier employs a distributed representation of labels, grouping potentially similar classes from the natural language view. The incorporation of dual classifiers transforms the proposed DCSL into a vision-language model, leveraging the semantic classifier to improve pseudo-labeling quality by identifying semantic relationships among class labels. Extensive tests on the publicly accessible AM defect dataset confirm that DCSL is more efficacious than state-of-the-art techniques for AM defect identification at the moment. The findings show that our DCSL is designed to enhance image discrimination skills towards label-free defect identification by training classifiers with different data perspectives in a synergistic manner. Given its innovative approach to defect detection, which can improve the effectiveness and precision of quality control and ultimately aid in the broad adoption of intelligent manufacturing across numerous industries, this study has the potential to herald in a new era of embodied intelligence in the current manufacturing system. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Intelligent Manufacturing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)*