Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention

通过多尺度层注意力机制增强甲骨文识别

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.

摘要： 甲骨文（OBI）识别对于理解中国古代文化具有至关重要的作用。然而，由于甲骨文形状复杂、不规则且往往存在残损，对其进行准确识别仍然极具挑战性。

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.

传统方法依赖于专家知识和人工分析，不仅耗时而且容易出错。尽管深度学习极大地推动了通用图像识别的发展，但现有方法难以捕捉甲骨文固有的细粒度细节和微妙变化，导致识别性能有限。

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.

即使是目前最新且有效的层注意力技术，虽然旨在通过增强层间交互来捕捉细粒度依赖关系，但在甲骨文识别任务中仍仅表现出微小的改进。

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.

为了解决这些局限性，我们提出了多尺度层注意力机制（MSLA），这是一种能够显式建模多尺度和跨层特征交互的新范式。通过在多个空间尺度上利用细粒度细节丰富特征表示，MSLA 实现了更准确、更稳健的甲骨文识别。

Extensive experiments on large-scale OBIs datasets demonstrate that MSLA consistently outperforms existing attention mechanisms while maintaining computational efficiency.

在大型甲骨文数据集上的大量实验表明，MSLA 在保持计算效率的同时，始终优于现有的注意力机制。