用一个模型同时识别草图并自动补全笔画，适合实时绘图场景。
SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion
- 用密集分类损失训练状态空间模型，实现边画边识别。
- 70%笔画完成时已达90%最终准确率，最终准确率达94.93%。
- 参数量仅155万，比变压器更轻量，适合嵌入式应用。
现有矢量草图模型将识别与生成分开处理，难以支持边画边理解的流式界面。我们提出SketchMamba，一种单一因果序列模型，可持续对任意部分草图进行分类，并同时生成后续笔画。通过在选择性状态空间主干上施加每步密集分类损失实现此目标。在Quick, Draw!数据集的58类子集上评估，SketchMamba达到94.93%的最终步准确率，渐进准确率曲线下面积（AUC）为0.706，在完成70%笔画时已超过其最终准确率的90%。在参数预算匹配条件下，155万参数的骨干网络性能与因果Transformer相当，优于循环和卷积基线。消融实验表明，密集监督机制而非架构本身驱动了早期预测能力。结果表明，单一因果隐状态可统一渐进识别与自回归生成，无需辅助编码器或任务特异性分支。
原文摘要 · Abstract (English)
Existing vector-sketch models treat recognition and generation as separate tasks, leaving a gap for streaming interfaces that must understand a drawing as it is being made. We present SketchMamba, a single causal sequence model that continuously classifies a sketch from any partial prefix while simultaneously generating its continuation. We achieve this by applying a dense per-step classification loss to a selective state-space backbone. Evaluated on a 58-class subset of the Quick, Draw! dataset, SketchMamba yields 94.93% final-step accuracy and a progressive-accuracy Area Under the Curve (AUC) of 0.706, crossing 90% of its final accuracy by the time 70% of the strokes are drawn. In a matched-budget comparison, the 1.55 million-parameter backbone ties a causal Transformer while outperforming recurrent and convolutional baselines. Ablations confirm that the dense supervision regime, rather than the architecture alone, drives the early-prediction capability. The results demonstrate that a single causal hidden state can unify progressive recognition and autoregressive generation without auxiliary encoders or task-specific branching.
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。