用逻辑规则优化弱监督分割，提升伪标签质量。
Weakly Supervised Segmentation as Semantic-Based Regularization
- 将弱标注与先验知识转为可微模糊逻辑约束，指导SAM优化
- 在Pascal VOC和REFUGE2上达到超越全监督基线的分割精度
- 适合需要低标注成本但高精度的医学或工业图像分割场景
弱监督语义分割（WSSS）从边界框、涂鸦或图像级标签等部分或粗略标注中训练像素级分割模型。尽管近期工作利用如通用分割模型（SAM）生成伪标签，但这些方法通常依赖启发式提示选择，且难以融入先验知识或异构标签。本文提出神经符号视角：将可微模糊逻辑与深度分割模型结合。弱标注和领域先验统一为连续逻辑约束，在弱监督下微调SAM。优化后的基础模型生成更高质量伪标签，进而训练无提示第二阶段分割模型。在Pascal VOC 2012和REFUGE2视盘/视杯分割数据集上的实验表明，该逻辑引导微调产生更高品质伪标签，实现超越全监督基线的分割准确率。
原文摘要 · Abstract (English)
Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes, scribbles, or image-level tags. While recent work leverages foundation models such as the Segment Anything Model (SAM) to generate pseudo-labels, these approaches typically depend on heuristic prompt choices and offer limited ways to incorporate prior knowledge or heterogeneous labels. We address this gap by taking a neurosymbolic perspective: integrating differentiable fuzzy logic with deep segmentation models. Weak annotations and domain-specific priors are unified as continuous logical constraints that fine-tune SAM under weak supervision. The refined foundation model then produces improved pseudo-labels, from which we train a second-stage prompt-free segmentation model. Experiments on Pascal VOC 2012 and the REFUGE2 optic disc/cup segmentation dataset show that our logic-guided fine-tuning yields higher-quality pseudo-labels, leading to state-of-the-art segmentation accuracy that often exceeds densely supervised baselines.
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。