# GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings

arXiv: https://arxiv.org/abs/2201.00625 · HTML: https://mlsanity.com/paper/2201.00625/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 3 Jan 2022.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Pay Less Attention with Lightweight and Dynamic Convolutions](https://mlsanity.com/paper/1901.10430/) (2019)
- [Local Relation Networks for Image Recognition](https://mlsanity.com/paper/1904.11491/) (2019)

## Built on by (most cited first, 13 of 13)

- [Symbol as Points: Panoptic Symbol Spotting via Point-based Representation](https://mlsanity.com/paper/2401.10556/) (2024)
- [PolyRoom: Room-aware Transformer for Floorplan Reconstruction](https://mlsanity.com/paper/2407.10439/) (2024)
- [PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs](https://mlsanity.com/paper/2308.05744/) (2023)
- [SymPoint Revolutionized: Boosting Panoptic Symbol Spotting with Layer Feature Enhancement](https://mlsanity.com/paper/2407.01928/) (2024)
- [ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting](https://mlsanity.com/paper/2503.22346/) (2025)
- [CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings](https://mlsanity.com/paper/2412.07377/) (2024)
- [Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings](https://mlsanity.com/paper/2505.23395/) (2025)
- [CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction](https://mlsanity.com/paper/2509.15459/) (2025)
- [Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images](https://mlsanity.com/paper/2404.10985/) (2024)
- [Text-Enhanced Panoptic Symbol Spotting in CAD Drawings](https://mlsanity.com/paper/2510.11091/) (2025)
- [Text-Aided Multi-Modal Panoptic Symbol Spotting for CAD Floor Plan Drawings](https://mlsanity.com/paper/2607.12678/) (2026)
- [PolarSym: Polar Geometry-aware Attention for CAD Floorplan Parsing](https://mlsanity.com/paper/2608.11793/) (2026)
- [Training-Free Agentic Computer Vision for Structural Component Detection in 2D Structural Framing Plans](https://mlsanity.com/paper/2608.17237/) (2026)

## Abstract (arXiv)

Spotting graphical symbols from the computer-aided design (CAD) drawings is essential to many industrial applications. Different from raster images, CAD drawings are vector graphics consisting of geometric primitives such as segments, arcs, and circles. By treating each CAD drawing as a graph, we propose a novel graph attention network GAT-CADNet to solve the panoptic symbol spotting problem: vertex features derived from the GAT branch are mapped to semantic labels, while their attention scores are cascaded and mapped to instance prediction. Our key contributions are three-fold: 1) the instance symbol spotting task is formulated as a subgraph detection problem and solved by predicting the adjacency matrix; 2) a relative spatial encoding (RSE) module explicitly encodes the relative positional and geometric relation among vertices to enhance the vertex attention; 3) a cascaded edge encoding (CEE) module extracts vertex attentions from multiple stages of GAT and treats them as edge encoding to predict the adjacency matrix. The proposed GAT-CADNet is intuitive yet effective and manages to solve the panoptic symbol spotting problem in one consolidated network. Extensive experiments and ablation studies on the public benchmark show that our graph-based approach surpasses existing state-of-the-art methods by a large margin.