用图结构直接识别草图，效率更高且准确率超87%。
SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition
- 将手绘草图建模为时空图，结合局部消息传递与高效全局注意力
- 在344类、344万张草图上达到83.6%至87.6%的准确率
- 内存降低40%以上，训练提速30%以上，适合大规模草图识别
本文从图原生视角研究大规模草图识别，将自由手绘草图直接建模为结构化图，而非栅格图像或笔画序列。提出SketchGraphNet，一种融合局部消息传递与内存高效的全局注意力机制的混合图神经架构，无需依赖辅助的位置或结构编码。为支持系统评估，构建了SketchGraph大规模基准数据集，包含344万张跨344类的图结构草图，分为两种变体（A和R）以反映不同噪声条件。每张草图表示为具有归一化笔画顺序属性的时空图。在SketchGraph-A和SketchGraph-R上，SketchGraphNet在统一训练配置下分别取得83.62%和87.61%的Top-1准确率。MemEffAttn相比Performer-based全局注意力，峰值GPU内存降低超过40%，训练时间减少超过30%，同时保持相近准确率。
原文摘要 · Abstract (English)
This work investigates large-scale sketch recognition from a graph-native perspective, where free-hand sketches are directly modeled as structured graphs rather than raster images or stroke sequences. We propose SketchGraphNet, a hybrid graph neural architecture that integrates local message passing with a memory-efficient global attention mechanism, without relying on auxiliary positional or structural encodings. To support systematic evaluation, we construct SketchGraph, a large-scale benchmark comprising 3.44 million graph-structured sketches across 344 categories, with two variants (A and R) to reflect different noise conditions. Each sketch is represented as a spatiotemporal graph with normalized stroke-order attributes. On SketchGraph-A and SketchGraph-R, SketchGraphNet achieves Top-1 accuracies of 83.62% and 87.61%, respectively, under a unified training configuration. MemEffAttn further reduces peak GPU memory by over 40% and training time by more than 30% compared with Performer-based global attention, while maintaining comparable accuracy.
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。