用统一模型先定位后识读，实现无检测器的电路图解析
Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models
- 先学定位再学内容，分阶段训练提升精度
- 严格定位F1提升0.0955，细胞识别准确率最高
- 适合需要全图解析的工业设计与自动化场景
PCB工程图包含稀疏图形、密集表格和依赖页面位置的文本。现有解析器多采用局部定位并裁剪送入专用识别器，导致漏检无法恢复。本文训练一个紧凑视觉语言模型，直接读取整页，输出区域类别、归一化框及文本或HTML内容。框坐标转为坐标标记用于监督。推理无需检测器或裁剪解析器。联合目标优化困难，因类别与框标记稀疏于长内容序列。采用定位优先课程学习，在加入内容目标前先掌握类-框格式，并通过内容感知重采样。在工程图数据集（ED dataset）固定验证集上，定位优先使严格定位F1相比联合训练提升0.0955（配对图像自举95%置信区间：[0.0350, 0.1572]）。G-Unified达到最低NED、最高单元格F1，唯一具有非零精确匹配得分。为全图电路图解析提供了无检测器基线。
原文摘要 · Abstract (English)
PCB engineering drawings mix sparse graphics, dense tables, and text whose meaning depends on page position. Localizing the regions and sending crops to specialized recognizers are determined as the methods for most parsers, so missed regions cannot be recovered downstream. We train a compact VLM to read the full page and get a sequence of region classes, normalized boxes, and text or HTML content. Bounding boxes are converted to coordinate tokens for supervision. Inference uses no detector or crop parser. The joint target is difficult to optimize because class and box tokens are sparse relative to the much longer content sequences. Our localization-first curriculum learns the class-box format before adding content targets with content-aware resampling. On the fixed validation split of the Engineering Drawing Dataset (ED dataset), Localization-First improves strict localization F1 by 0.0955 over joint training (paired image-bootstrap 95% interval: [0.0350, 0.1572]). G-Unified has the lowest NED, highest cell F1, and only nonzero exact-match score. It provides a detector-free baseline for full-page PCB drawing parsing.
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。