University of Leicester
Browse
Archeology.pdf (3.78 MB)

Learning from scarce information: using synthetic data to classify Roman fine ware pottery

Download (3.78 MB)
journal contribution
posted on 2021-09-16, 09:03 authored by Santos Nunez Jareno, Daniel P. van Helden, Evgeny Mirkes, Ivan Tyukin, Penelope Allison
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.

History

Citation

Entropy 2021,23,1140. https://doi.org/10.3390/e23091140

Author affiliation

School of Archaeology and Ancient History

Version

  • VoR (Version of Record)

Published in

Entropy: international and interdisciplinary journal of entropy and information studies

Volume

23

Issue

9

Pagination

1140

Publisher

MDPI AG

issn

1099-4300

Acceptance date

2021-08-17

Copyright date

2021

Available date

2021-09-16

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC