改进表格识别的指针损失，让模型更关注相邻单元格
Rethinking the Pointer Loss in Table Structure Recognition: Geometry-Aware Pointer Loss for Spatial Locality
- 根据空间邻近度重新加权交叉熵损失
- 相邻单元格错误率降低，达新最优性能
- 无需修改模型，适合表格结构识别研究者
使用指针网络进行表格结构识别（TSR）可生成HTML序列并匹配标签与检测到的文本（或单元格）区域，取得优异效果。然而分析发现，当指针网络出错时，79.6%的错误发生在空间相邻的单元格间（曼哈顿距离≤2）。尽管如此，标准交叉熵损失对所有负样本一视同仁。本文提出几何感知指针损失（GAP Loss），基于与真实位置的空间距离重加权交叉熵目标。通过反距离加权，使梯度聚焦在模型最困难的位置：邻近单元格获得更强梯度，远距离单元格则弱化。该方法仅需对损失计算进行简单修改，保持原有模型架构，推理成本零增加。在PubTabNet和SynthTabNet上的大量实验表明，GAP能持续降低相邻单元格错误，实现新基准性能。结果表明，在损失层面引入几何先验是一种简单而有效的鲁棒性提升策略。代码已开源：https://github.com/teamreboott/GAP
原文摘要 · Abstract (English)
Table Structure Recognition (TSR) using a pointer network achieves impressive results by predicting HTML sequences while aligning tags to detected text (or cell) regions. However, our analysis reveals that when pointer networks fail, 79.6% of errors occur between spatially adjacent cells (Manhattan distance <= 2). Despite this, standard cross-entropy loss weights all negative candidates equally. In this work, we propose Geometry-Aware Pointer (GAP) Loss, which reweights the cross-entropy objective based on spatial proximity to ground truth. By applying inverse distance weighting, GAP focuses gradient flow where the model struggles most: immediate neighbors receive stronger gradients than distant cells. Our approach requires only a straightforward modification to the loss computation, maintaining the same model architecture with zero additional inference cost. Extensive experiments on PubTabNet and SynthTabNet demonstrate that GAP consistently reduces adjacent-cell errors, achieving new state-of-the-art performance. Our findings suggest that incorporating geometric inductive biases at the loss level provides a simple yet effective approach to robust TSR. Our code is available at https://github.com/teamreboott/GAP
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。