Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.10104 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916396195119104 |
|---|---|
| author | Fraunholz, Thomas Rall, Dennis Köhler, Tim Schuster, Alfons Mayer, Monika Larsen, Lars |
| author_facet | Fraunholz, Thomas Rall, Dennis Köhler, Tim Schuster, Alfons Mayer, Monika Larsen, Lars |
| contents | In the realm of industrial manufacturing, Artificial Intelligence (AI) is playing an increasing role, from automating existing processes to aiding in the development of new materials and techniques. However, a significant challenge arises in smaller, experimental processes characterized by limited training data availability, questioning the possibility to train AI models in such small data contexts. In this work, we explore the potential of Transfer Learning to address this challenge, specifically investigating the minimum amount of data required to develop a functional AI model. For this purpose, we consider the use case of quality control of Carbon Fiber Reinforced Polymer (CFRP) tape laying in aerospace manufacturing using optical sensors. We investigate the behavior of different open-source computer vision models with a continuous reduction of the training data. Our results show that the amount of data required to successfully train an AI model can be drastically reduced, and the use of smaller models does not necessarily lead to a loss of performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10104 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Comparative Study of Open Source Computer Vision Models for Application on Small Data: The Case of CFRP Tape Laying Fraunholz, Thomas Rall, Dennis Köhler, Tim Schuster, Alfons Mayer, Monika Larsen, Lars Computer Vision and Pattern Recognition Machine Learning 68T05, 93A30, 74E30 I.2.6; I.4.8; J.2 In the realm of industrial manufacturing, Artificial Intelligence (AI) is playing an increasing role, from automating existing processes to aiding in the development of new materials and techniques. However, a significant challenge arises in smaller, experimental processes characterized by limited training data availability, questioning the possibility to train AI models in such small data contexts. In this work, we explore the potential of Transfer Learning to address this challenge, specifically investigating the minimum amount of data required to develop a functional AI model. For this purpose, we consider the use case of quality control of Carbon Fiber Reinforced Polymer (CFRP) tape laying in aerospace manufacturing using optical sensors. We investigate the behavior of different open-source computer vision models with a continuous reduction of the training data. Our results show that the amount of data required to successfully train an AI model can be drastically reduced, and the use of smaller models does not necessarily lead to a loss of performance. |
| title | A Comparative Study of Open Source Computer Vision Models for Application on Small Data: The Case of CFRP Tape Laying |
| topic | Computer Vision and Pattern Recognition Machine Learning 68T05, 93A30, 74E30 I.2.6; I.4.8; J.2 |
| url | https://arxiv.org/abs/2409.10104 |