用大间距损失和启发式规则提升文档结构解析准确率
Hierarchical Document Parsing via Large Margin Feature Matching and Heuristics
- 结合大间距损失与贪婪算法，增强特征区分度
- 私有榜单准确率达0.98904，显著优于基线
- 适合需要高效高精度文档结构解析的研究者
我们提交的解决方案在AAAI-25 VRD-IU挑战赛中获得第一名。方法融合大间距损失以增强特征判别力，并利用启发式规则优化层级关系。通过深度学习匹配策略与贪心算法结合，在保持计算效率的同时显著提升准确率。在私有榜单上达到0.98904的准确率，证明了其在文档结构解析中的有效性。源代码已公开于https://github.com/ffyyytt/VRUID-AAAI-DAKiet。
原文摘要 · Abstract (English)
We present our solution to the AAAI-25 VRD-IU challenge, achieving first place in the competition. Our approach integrates large margin loss for improved feature discrimination and employs heuristic rules to refine hierarchical relationships. By combining a deep learning-based matching strategy with greedy algorithms, we achieve a significant boost in accuracy while maintaining computational efficiency. Our method attains an accuracy of 0.98904 on the private leaderboard, demonstrating its effectiveness in document structure parsing. Source codes are publicly available at https://github.com/ffyyytt/VRUID-AAAI-DAKiet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。