260327 Enhance publishing | Decoupled Learning for Long-tailed Oracle Bone Character Recognition Based on Adaptive Difficulty Sampling——Code

Methods

The framework separates representation learning from classifier optimization. In the first stage, the backbone is trained using mixed augmentation (CutMix and RandAug) and label-distribution-aware margin (LDAM) loss to extract robust features and mitigate intra-class variance. In the second stage, the backbone is frozen.

The classifier is optimized utilizing a novel class-difficulty-based adaptive sampling strategy, which dynamically allocates sampling weights based on historical training loss, coupled with a class-balanced loss (CBL) to refine decision boundaries.Results and Discussions Experiments on the highly imbalanced OBC306 dataset demonstrate that the proposed method achieves an overall accuracy of 94.34% and an average class accuracy of 89.89%.

It significantly outperforms the Inception-v4 baseline by 19.61% in average class accuracy. Comprehensive ablation studies validatethat the difficulty sampling strategy successfully boosts the recognition of rare and challenging characters. Additionally, sensitivity and qualitative analyses further confirm the robustness and interpretability of the model.Conclusions The proposed decoupled learning algorithm effectively addresses long-tailed OBC recognition by balancing learning priorities across diverse classes.

Mixed augmentation enriches sample diversity, while difficulty-aware sampling refines decision boundaries for complex tail characters without sacrificing head class performance. This framework provides a highly robust and scalable solution for the digital recognition of ancient scripts and archaeological AI applications.