aiqbench analysis
This research addresses data scarcity in industrial manufacturing by applying semi-supervised learning techniques to transformer-based Computer-Aided Process Planning (CAPP) models. The proposed method utilizes an oracle to filter pseudo-labels from unseen parts, enabling effective one-shot retraining without extensive manual annotation. This approach demonstrates consistent accuracy improvements specifically for AI applications in resource-constrained environments.
Semi-supervised CAPP Transformer Learning via Pseudo-labeling
arXiv:2602.01419v2 Announce Type: replace-cross Abstract: High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments.
Abstract:High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2602.01419 [cs.LG]
(or arXiv:2602.01419v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2602.01419 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 181 words
Related coverage
MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal Prostate MRI Segmentation
arXiv · Aug 21, 2026
SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking
arXiv · Aug 18, 2026
Lightweight Machine Learning-Driven Monocular Sidewalk Path Extraction for Embedded Micromobility Navigation
arXiv · Aug 27, 2026
BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio
arXiv · Sep 28, 2026