LASA：一种用于开放词汇场景草图语义分割的弱监督方法
LASA: A Weak Supervision Method for Open-Vocabulary Scene Sketch Semantic Segmentation
AI总结：
提出LASA方法，通过跨层聚合Vision Transformer注意力图，在弱监督下实现开放词汇场景草图的语义分割，显著提升分割精度和空间一致性。
摘要：
开放词汇场景草图语义分割旨在基于推理时指定的灵活类别词汇，为稀疏线条图分配密集语义标签，而无需在训练期间依赖像素级标注。与自然图像不同，草图缺乏纹理和颜色线索，使得语义理解严重依赖于笔画布局和空间配置，这一挑战导致单层视觉-语言特征本质上不稳定。我们的关键观察是，来自不同Vision Transformer层的注意力图编码了互补的空间线索：浅层捕获全局结构布局，而深层聚焦于局部笔画交叉和物体部件。这表明跨层聚合比任何单独一层提供了更稳健的结构先验。利用这一洞察，我们提出了一种结构感知框架，基于\textbf{逐层累积结构注意力}（\textbf{LASA}），该框架聚合多层注意力以在弱监督下指导层次化语义对齐，并在推理期间细化预测。在FS-COCO、SFSD和FrISS上的实验表明，与先前的弱监督基线相比，LASA将mIoU分别提高了+3.43、+8.01和+15.74，在分割精度和空间一致性上均表现出一致的提升。我们的源代码将公开提供。
英文摘要：
Open-vocabulary scene sketch semantic segmentation aims to assign dense semantic labels to sparse line drawings based on flexible category vocabularies specified at inference time, without relying on pixel-level annotations during training. Unlike natural images, sketches lack texture and color cues, making semantic understanding heavily dependent on stroke layout and spatial configuration, a challenge that renders single-layer vision-language features inherently unstable. Our key observation is that attention maps from different Vision Transformer layers encode complementary spatial cues: shallow layers capture global structural layouts, while deeper layers focus on local stroke intersections and object parts. This suggests that cross-layer aggregation provides a more robust structural prior than any individual layer alone. Leveraging this insight, we propose a structure-aware framework built upon \textbf{L}ayer-wise \textbf{A}ccumulated \textbf{S}tructural \textbf{A}ttention (\textbf{LASA}), which aggregates multi-layer attention to guide hierarchical semantic alignment under weak supervision and refine predictions during inference. Experiments on FS-COCO, SFSD, and FrISS show that LASA improves mIoU by $+3.43$, $+8.01$, and $+15.74$ over the prior weakly supervised baselines, demonstrating consistent gains in both segmentation accuracy and spatial coherence. Our source code will be made publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
