首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery
Authors:Santos J Núez Jareo  Daniël P van Helden  Evgeny M Mirkes  Ivan Y Tyukin  Penelope M Allison
Institution:1.School of Mathematics and Actuarial Science, University of Leicester, Leicester LE1 7RH, UK; (S.J.N.J.); (E.M.M.);2.School of Archaeology and Ancient History, University of Leicester, Leicester LE1 7RH, UK; (D.P.v.H.); (P.M.A.);3.Laboratory of Advanced Methods for High-Dimensional Data Analysis, Lobachevsky University, 603105 Nizhni Novgorod, Russia
Abstract:In this article, we consider a version of the challenging problem of learning from datasets whose size is too limited to allow generalisation beyond the training set. To address the challenge, we propose to use a transfer learning approach whereby the model is first trained on a synthetic dataset replicating features of the original objects. In this study, the objects were smartphone photographs of near-complete Roman terra sigillata pottery vessels from the collection of the Museum of London. Taking the replicated features from published profile drawings of pottery forms allowed the integration of expert knowledge into the process through our synthetic data generator. After this first initial training the model was fine-tuned with data from photographs of real vessels. We show, through exhaustive experiments across several popular deep learning architectures, different test priors, and considering the impact of the photograph viewpoint and excessive damage to the vessels, that the proposed hybrid approach enables the creation of classifiers with appropriate generalisation performance. This performance is significantly better than that of classifiers trained exclusively on the original data, which shows the promise of the approach to alleviate the fundamental issue of learning from small datasets.
Keywords:deep learning  machine learning  image classification  simulated data  learning from scarce information  Roman pottery (terra sigillata)
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号