Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention

2026-06-30

AI Summary

This work addresses the challenges of oracle bone script recognition, which stem from highly complex and often severely damaged character forms that render traditional methods inefficient and hinder existing deep learning models from effectively capturing fine-grained structural features. To overcome these limitations, the authors propose a Multi-Scale Layer Attention (MSLA) mechanism that explicitly models interactions across network layers and multi-scale spatial features, thereby enhancing the representation of subtle deformations and local structures inherent in oracle bone characters. Evaluated on a large-scale oracle bone script dataset, the proposed method significantly outperforms current attention-based approaches, achieving higher recognition accuracy and robustness while maintaining computational efficiency, thus breaking through the prevailing performance bottleneck in this domain.

Abstract

Oracle Bone Inscriptions (OBIs) recognition plays a crucial role in understanding ancient Chinese culture. However, accurately recognizing OBIs remains highly challenging due to their complex, irregular, and often degraded shapes. Traditional methods rely on expert knowledge and manual analysis, which are time-consuming and error-prone. Although deep learning has greatly advanced general image recognition, existing methods struggle to capture the fine-grained details and subtle variations inherent in OBIs, resulting in limited performance. Even most recent and effective layer attention techniques are designed to capture fine-grained dependencies through enhanced inter-layer interactions, yet they still exhibit only marginal improvements in OBIs recognition. To address these limitations, we propose Multi-Scale Layer Attention (MSLA), a novel paradigm that explicitly models both multi-scale and cross-layer feature interactions. By enriching the representation with fine-grained details across multiple spatial scales, MSLA enables more accurate and robust OBIs recognition. Extensive experiments on large-scale OBIs datasets demonstrate that MSLA consistently outperforms existing attention mechanisms while maintaining computational efficiency.

Problem

• Oracle Bone Inscriptions
• recognition
• fine-grained details
• irregular shapes
• degraded characters

Innovation

• Multi-Scale Layer Attention
• Oracle Bone Inscription Recognition
• Fine-Grained Feature Interaction
• Cross-Layer Attention
• Deep Learning for Ancient Scripts