SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion

arXiv:2607.23580v1 Announce Type: new Abstract: 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.

Related

• DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization
• DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding
• LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
• Bridging Data Trials and Task Barriers: A Unified Framework for Sketch Biometric Identification
• Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection

Source: arXiv cs.CV | 2026-07-28