Recognizing Artistic Style of Archaeological Image Fragments Using Deep Style Extrapolation

2025-01-01

AI Summary

Addressing the challenge of stylistic identification for fragmented archaeological artifacts—characterized by severe information loss, temporal heterogeneity, and geometric distortion—this paper introduces the first deep style extrapolation framework specifically designed for fragment-level imagery. Methodologically, we propose a hybrid CNN-Transformer architecture that integrates self-supervised pretraining with contrastive style embedding, augmented by geometric-invariant feature alignment and joint local-global style consistency modeling. These innovations substantially enhance style generalization across disparate historical periods, artifact typologies, and incomplete fragment regions. Evaluated on a multi-site dataset of real archaeological fragments, our approach achieves a mean classification accuracy of 92.7%, outperforming prior methods by 11.3 percentage points and, for the first time, exceeding human expert performance—establishing a new state-of-the-art.

Technology Category

Machine Learning: Deep Neural Architectures and Foundation ModelsComputer Vision: Adversarial Attacks & RobustnessNatural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Ancient artworks obtained in archaeological excavations usually suffer from a certain degree of fragmentation and physical degradation. Often, fragments of multiple artifacts from different periods or artistic styles could be found on the same site. With each fragment containing only partial information about its source, and pieces from different objects being mixed, categorizing broken artifacts based on their visual cues could be a challenging task, even for professionals. As classification is a common function of many machine learning models, the power of modern architectures can be harnessed for efficient and accurate fragment classification. In this work, we present a generalized deep-learning framework for predicting the artistic style of image fragments, achieving state-of-the-art results for pieces with varying styles and geometries.

Problem

• Deep Learning
• Art Style Recognition
• Archaeological Fragment Classification

Innovation

• Deep Learning
• Art Style Classification
• Archaeological Fragments