Abstract

In recent years, machine learning approaches have been used to classify and extract style from media and have been used to reinforce known chronologies from classical art history. In this work we employ the first ever machine learning analysis of Australian rock art using a data efficient transfer learning approach to identify features suitable for distinguishing styles of rock art. These features are evaluated in a one-shot learning setting. Results demonstrate that known Arnhem Land Rock art styles can be resolved without knowledge of prior groupings. We then analyse the activation space of learned features and report on the relationships between styles and arrange these classes into a stylistic chronology based on distance within the activation space. By generating a stylistic chronology, it is shown that the model is sensitive to both temporal and spatial patterns in the distribution of rock art in the Arnhem Land Plateau region. More broadly, this approach is ideally suited to evaluating style within any material culture assemblage and overcomes the common constraint of small training data sets in archaeological machine learning studies.

摘要

近年来，机器学习方法已被用于从媒体中分类和提取风格，并已被用于强化古典艺术史中已知的年表。在这项工作中，我们使用数据高效的迁移学习方法对澳大利亚岩画进行了首次机器学习分析，以识别适合区分岩画风格的特征。这些功能在一次性学习设置中进行评估。结果表明，已知的 Arnhem Land Rock 艺术风格可以在不了解先前分组的情况下解决。然后我们分析学习特征的激活空间并报告样式之间的关系，并根据激活空间内的距离将这些类排列成文体年表。通过生成风格年表，结果表明，该模型对阿纳姆高原地区岩画分布的时空格局均敏感。更广泛地说，这种方法非常适合评估任何物质文化组合中的风格，并克服了考古机器学习研究中小训练数据集的常见限制。